Merge branch 'master' of git://git.denx.de/u-boot-x86

32 files changed, 6470 insertions, 730 deletions

diff --git a/arch/x86/cpu/Makefile b/arch/x86/cpu/Makefile
index 62e43c04e5..6ded0a7f0f 100644
--- a/arch/x86/cpu/Makefile
+++ b/arch/x86/cpu/Makefile
@@ -12,9 +12,11 @@ extra-y	= start.o
 obj-$(CONFIG_X86_RESET_VECTOR) += resetvec.o start16.o
 obj-y	+= interrupts.o cpu.o call64.o
 
+obj-$(CONFIG_INTEL_BAYTRAIL) += baytrail/
 obj-$(CONFIG_SYS_COREBOOT) += coreboot/
 obj-$(CONFIG_NORTHBRIDGE_INTEL_SANDYBRIDGE) += ivybridge/
 obj-$(CONFIG_NORTHBRIDGE_INTEL_IVYBRIDGE) += ivybridge/
+obj-$(CONFIG_INTEL_QUARK) += quark/
 obj-$(CONFIG_INTEL_QUEENSBAY) += queensbay/
 obj-y += lapic.o
 obj-y += mtrr.o
diff --git a/arch/x86/cpu/baytrail/Kconfig b/arch/x86/cpu/baytrail/Kconfig
new file mode 100644
index 0000000000..e86cc01115
--- /dev/null
+++ b/arch/x86/cpu/baytrail/Kconfig
@@ -0,0 +1,9 @@
+#
+# Copyright (C) 2015 Google, Inc
+#
+# SPDX-License-Identifier:	GPL-2.0+
+#
+
+config INTEL_BAYTRAIL
+	bool
+	select HAVE_FSP
diff --git a/arch/x86/cpu/baytrail/Makefile b/arch/x86/cpu/baytrail/Makefile
new file mode 100644
index 0000000000..8914e8b6d5
--- /dev/null
+++ b/arch/x86/cpu/baytrail/Makefile
@@ -0,0 +1,10 @@
+#
+# Copyright (C) 2015 Google, Inc
+#
+# SPDX-License-Identifier:	GPL-2.0+
+#
+
+obj-y += early_uart.o
+obj-y += fsp_configs.o
+obj-y += pci.o
+obj-y += valleyview.o
diff --git a/arch/x86/cpu/baytrail/early_uart.c b/arch/x86/cpu/baytrail/early_uart.c
new file mode 100644
index 0000000000..41992105fe
--- /dev/null
+++ b/arch/x86/cpu/baytrail/early_uart.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2015 Google, Inc
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <errno.h>
+#include <asm/io.h>
+
+#define PCI_DEV_CONFIG(segbus, dev, fn) ( \
+		(((segbus) & 0xfff) << 20) | \
+		(((dev) & 0x1f) << 15) | \
+		(((fn)  & 0x07) << 12))
+
+/* Platform Controller Unit */
+#define LPC_DEV			0x1f
+#define LPC_FUNC		0
+
+/* Enable UART */
+#define UART_CONT		0x80
+
+/* SCORE Pad definitions */
+#define UART_RXD_PAD			82
+#define UART_TXD_PAD			83
+
+/* Pad base: PAD_CONF0[n]= PAD_BASE + 16 * n */
+#define GPSCORE_PAD_BASE	(IO_BASE_ADDRESS + IO_BASE_OFFSET_GPSCORE)
+
+/* IO Memory */
+#define IO_BASE_ADDRESS			0xfed0c000
+#define  IO_BASE_OFFSET_GPSCORE		0x0000
+#define  IO_BASE_OFFSET_GPNCORE		0x1000
+#define  IO_BASE_OFFSET_GPSSUS		0x2000
+#define IO_BASE_SIZE			0x4000
+
+static inline unsigned int score_pconf0(int pad_num)
+{
+	return GPSCORE_PAD_BASE + pad_num * 16;
+}
+
+static void score_select_func(int pad, int func)
+{
+	uint32_t reg;
+	uint32_t pconf0_addr = score_pconf0(pad);
+
+	reg = readl(pconf0_addr);
+	reg &= ~0x7;
+	reg |= func & 0x7;
+	writel(reg, pconf0_addr);
+}
+
+static void pci_write_config32(int dev, unsigned int where, u32 value)
+{
+	unsigned long addr;
+
+	addr = CONFIG_PCIE_ECAM_BASE | dev | (where & ~3);
+	writel(value, addr);
+}
+
+/* This can be called after memory-mapped PCI is working */
+int setup_early_uart(void)
+{
+	/* Enable the legacy UART hardware. */
+	pci_write_config32(PCI_DEV_CONFIG(0, LPC_DEV, LPC_FUNC), UART_CONT, 1);
+
+	/*
+	 * Set up the pads to the UART function. This allows the signals to
+	 * leave the chip
+	 */
+	score_select_func(UART_RXD_PAD, 1);
+	score_select_func(UART_TXD_PAD, 1);
+
+	/* TODO(sjg@chromium.org): Call debug_uart_init() */
+
+	return 0;
+}
diff --git a/arch/x86/cpu/baytrail/fsp_configs.c b/arch/x86/cpu/baytrail/fsp_configs.c
new file mode 100644
index 0000000000..86b6926272
--- /dev/null
+++ b/arch/x86/cpu/baytrail/fsp_configs.c
@@ -0,0 +1,156 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2014, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+#include <common.h>
+#include <asm/arch/fsp/azalia.h>
+#include <asm/fsp/fsp_support.h>
+
+/* ALC262 Verb Table - 10EC0262 */
+static const uint32_t verb_table_data13[] = {
+	/* Pin Complex (NID 0x11) */
+	0x01171cf0,
+	0x01171d11,
+	0x01171e11,
+	0x01171f41,
+	/* Pin Complex (NID 0x12) */
+	0x01271cf0,
+	0x01271d11,
+	0x01271e11,
+	0x01271f41,
+	/* Pin Complex (NID 0x14) */
+	0x01471c10,
+	0x01471d40,
+	0x01471e01,
+	0x01471f01,
+	/* Pin Complex (NID 0x15) */
+	0x01571cf0,
+	0x01571d11,
+	0x01571e11,
+	0x01571f41,
+	/* Pin Complex (NID 0x16) */
+	0x01671cf0,
+	0x01671d11,
+	0x01671e11,
+	0x01671f41,
+	/* Pin Complex (NID 0x18) */
+	0x01871c20,
+	0x01871d98,
+	0x01871ea1,
+	0x01871f01,
+	/* Pin Complex (NID 0x19) */
+	0x01971c21,
+	0x01971d98,
+	0x01971ea1,
+	0x01971f02,
+	/* Pin Complex (NID 0x1A) */
+	0x01a71c2f,
+	0x01a71d30,
+	0x01a71e81,
+	0x01a71f01,
+	/* Pin Complex */
+	0x01b71c1f,
+	0x01b71d40,
+	0x01b71e21,
+	0x01b71f02,
+	/* Pin Complex */
+	0x01c71cf0,
+	0x01c71d11,
+	0x01c71e11,
+	0x01c71f41,
+	/* Pin Complex */
+	0x01d71c01,
+	0x01d71dc6,
+	0x01d71e14,
+	0x01d71f40,
+	/* Pin Complex */
+	0x01e71cf0,
+	0x01e71d11,
+	0x01e71e11,
+	0x01e71f41,
+	/* Pin Complex */
+	0x01f71cf0,
+	0x01f71d11,
+	0x01f71e11,
+	0x01f71f41,
+};
+
+/*
+ * This needs to be in ROM since if we put it in CAR, FSP init loses it when
+ * it drops CAR.
+ *
+ * TODO(sjg@chromium.org): Move to device tree when FSP allows it
+ *
+ * VerbTable: (RealTek ALC262)
+ * Revision ID = 0xFF, support all steps
+ * Codec Verb Table For AZALIA
+ * Codec Address: CAd value (0/1/2)
+ * Codec Vendor: 0x10EC0262
+ */
+static const struct pch_azalia_verb_table azalia_verb_table[] = {
+	{
+		{
+			0x10ec0262,
+			0x0000,
+			0xff,
+			0x01,
+			0x000b,
+			0x0002,
+		},
+		verb_table_data13
+	}
+};
+
+const struct pch_azalia_config azalia_config = {
+	.pme_enable = 1,
+	.docking_supported = 1,
+	.docking_attached = 0,
+	.hdmi_codec_enable = 1,
+	.azalia_v_ci_enable = 1,
+	.rsvdbits = 0,
+	.azalia_verb_table_num = 1,
+	.azalia_verb_table = azalia_verb_table,
+	.reset_wait_timer_us = 300
+};
+
+void update_fsp_upd(struct upd_region *fsp_upd)
+{
+	struct memory_down_data *mem;
+
+	/*
+	 * Configure everything here to avoid the poor hard-pressed user
+	 * needing to run Intel's binary configuration tool. It may also allow
+	 * us to support the 1GB single core variant easily.
+	 *
+	 * TODO(sjg@chromium.org): Move to device tree
+	 */
+	fsp_upd->mrc_init_tseg_size = 8;
+	fsp_upd->mrc_init_mmio_size = 0x800;
+	fsp_upd->emmc_boot_mode = 0xff;
+	fsp_upd->enable_sdio = 1;
+	fsp_upd->enable_sdcard = 1;
+	fsp_upd->enable_hsuart0 = 1;
+	fsp_upd->azalia_config_ptr = (uint32_t)&azalia_config;
+	fsp_upd->enable_i2_c0 = 0;
+	fsp_upd->enable_i2_c2 = 0;
+	fsp_upd->enable_i2_c3 = 0;
+	fsp_upd->enable_i2_c4 = 0;
+	fsp_upd->enable_xhci = 0;
+	fsp_upd->igd_render_standby = 1;
+
+	mem = &fsp_upd->memory_params;
+	mem->enable_memory_down = 1;
+	mem->dram_speed = 1;
+	mem->dimm_width = 1;
+	mem->dimm_density = 2;
+	mem->dimm_tcl = 0xb;
+	mem->dimm_trpt_rcd = 0xb;
+	mem->dimm_twr = 0xc;
+	mem->dimm_twtr = 6;
+	mem->dimm_trrd = 6;
+	mem->dimm_trtp = 6;
+	mem->dimm_tfaw = 0x14;
+}
diff --git a/arch/x86/cpu/baytrail/pci.c b/arch/x86/cpu/baytrail/pci.c
new file mode 100644
index 0000000000..6c291f9ee9
--- /dev/null
+++ b/arch/x86/cpu/baytrail/pci.c
@@ -0,0 +1,46 @@
+/*
+ * Copyright (C) 2014, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <pci.h>
+#include <asm/pci.h>
+#include <asm/fsp/fsp_support.h>
+
+DECLARE_GLOBAL_DATA_PTR;
+
+void board_pci_setup_hose(struct pci_controller *hose)
+{
+	hose->first_busno = 0;
+	hose->last_busno = 0;
+
+	/* PCI memory space */
+	pci_set_region(hose->regions + 0,
+		       CONFIG_PCI_MEM_BUS,
+		       CONFIG_PCI_MEM_PHYS,
+		       CONFIG_PCI_MEM_SIZE,
+		       PCI_REGION_MEM);
+
+	/* PCI IO space */
+	pci_set_region(hose->regions + 1,
+		       CONFIG_PCI_IO_BUS,
+		       CONFIG_PCI_IO_PHYS,
+		       CONFIG_PCI_IO_SIZE,
+		       PCI_REGION_IO);
+
+	pci_set_region(hose->regions + 2,
+		       CONFIG_PCI_PREF_BUS,
+		       CONFIG_PCI_PREF_PHYS,
+		       CONFIG_PCI_PREF_SIZE,
+		       PCI_REGION_PREFETCH);
+
+	pci_set_region(hose->regions + 3,
+		       0,
+		       0,
+		       gd->ram_size,
+		       PCI_REGION_MEM | PCI_REGION_SYS_MEMORY);
+
+	hose->region_count = 4;
+}
diff --git a/arch/x86/cpu/baytrail/valleyview.c b/arch/x86/cpu/baytrail/valleyview.c
new file mode 100644
index 0000000000..a3e837d43e
--- /dev/null
+++ b/arch/x86/cpu/baytrail/valleyview.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2014, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <mmc.h>
+#include <pci_ids.h>
+#include <asm/post.h>
+
+static struct pci_device_id mmc_supported[] = {
+	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VALLEYVIEW_SDIO },
+	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VALLEYVIEW_SDCARD },
+};
+
+int cpu_mmc_init(bd_t *bis)
+{
+	printf("mmc init\n");
+	return pci_mmc_init("ValleyView SDHCI", mmc_supported,
+			    ARRAY_SIZE(mmc_supported));
+}
+
+int arch_cpu_init(void)
+{
+	int ret;
+
+	post_code(POST_CPU_INIT);
+#ifdef CONFIG_SYS_X86_TSC_TIMER
+	timer_set_base(rdtsc());
+#endif
+
+	ret = x86_cpu_init_f();
+	if (ret)
+		return ret;
+
+	return 0;
+}
diff --git a/arch/x86/cpu/ivybridge/gma.c b/arch/x86/cpu/ivybridge/gma.c
index 6cf9654e02..821ea25019 100644
--- a/arch/x86/cpu/ivybridge/gma.c
+++ b/arch/x86/cpu/ivybridge/gma.c
@@ -758,7 +758,8 @@ int gma_func0_init(pci_dev_t dev, struct pci_controller *hose,
 
 #ifdef CONFIG_VIDEO
 	start = get_timer(0);
-	ret = pci_run_vga_bios(dev, int15_handler, false);
+	ret = pci_run_vga_bios(dev, int15_handler, PCI_ROM_USE_NATIVE |
+			       PCI_ROM_ALLOW_FALLBACK);
 	debug("BIOS ran in %lums\n", get_timer(start));
 #endif
 	/* Post VBIOS init */
diff --git a/arch/x86/cpu/ivybridge/sdram.c b/arch/x86/cpu/ivybridge/sdram.c
index 49634485f3..766b385c25 100644
--- a/arch/x86/cpu/ivybridge/sdram.c
+++ b/arch/x86/cpu/ivybridge/sdram.c
@@ -757,7 +757,7 @@ int dram_init(void)
 		.mchbar = DEFAULT_MCHBAR,
 		.dmibar = DEFAULT_DMIBAR,
 		.epbar = DEFAULT_EPBAR,
-		.pciexbar = CONFIG_MMCONF_BASE_ADDRESS,
+		.pciexbar = CONFIG_PCIE_ECAM_BASE,
 		.smbusbar = SMBUS_IO_BASE,
 		.wdbbar = 0x4000000,
 		.wdbsize = 0x1000,
diff --git a/arch/x86/cpu/quark/Kconfig b/arch/x86/cpu/quark/Kconfig
new file mode 100644
index 0000000000..bc961ef07c
--- /dev/null
+++ b/arch/x86/cpu/quark/Kconfig
@@ -0,0 +1,126 @@
+#
+# Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+#
+# SPDX-License-Identifier:	GPL-2.0+
+#
+
+config INTEL_QUARK
+	bool
+	select HAVE_RMU
+	select TSC_CALIBRATION_BYPASS
+
+if INTEL_QUARK
+
+config HAVE_RMU
+	bool "Add a Remote Management Unit (RMU) binary"
+	help
+	  Select this option to add a Remote Management Unit (RMU) binary
+	  to the resulting U-Boot image. It is a data block (up to 64K) of
+	  machine-specific code which must be put in the flash for the RMU
+	  within the Quark SoC processor to access when powered up before
+	  system BIOS is executed.
+
+config RMU_FILE
+	string "Remote Management Unit (RMU) binary filename"
+	depends on HAVE_RMU
+	default "rmu.bin"
+	help
+	  The filename of the file to use as Remote Management Unit (RMU)
+	  binary in the board directory.
+
+config RMU_ADDR
+	hex "Remote Management Unit (RMU) binary location"
+	depends on HAVE_RMU
+	default 0xfff00000
+	help
+	  The location of the RMU binary is determined by a strap. It must be
+	  put in flash at a location matching the strap-determined base address.
+
+	  The default base address of 0xfff00000 indicates that the binary must
+	  be located at offset 0 from the beginning of a 1MB flash device.
+
+config HAVE_CMC
+	bool
+	default HAVE_RMU
+
+config CMC_FILE
+	string
+	depends on HAVE_CMC
+	default RMU_FILE
+
+config CMC_ADDR
+	hex
+	depends on HAVE_CMC
+	default RMU_ADDR
+
+config ESRAM_BASE
+	hex
+	default 0x80000000
+	help
+	  Embedded SRAM (eSRAM) memory-mapped base address.
+
+config PCIE_ECAM_BASE
+	hex
+	default 0xe0000000
+
+config RCBA_BASE
+	hex
+	default 0xfed1c000
+	help
+	  Root Complex register block memory-mapped base address.
+
+config ACPI_PM1_BASE
+	hex
+	default 0x1000
+	help
+	  ACPI Power Managment 1 (PM1) i/o-mapped base address.
+	  This device is defined in ACPI specification, with 16 bytes in size.
+
+config ACPI_PBLK_BASE
+	hex
+	default 0x1010
+	help
+	  ACPI Processor Block (PBLK) i/o-mapped base address.
+	  This device is defined in ACPI specification, with 16 bytes in size.
+
+config SPI_DMA_BASE
+	hex
+	default 0x1020
+	help
+	  SPI DMA i/o-mapped base address.
+
+config GPIO_BASE
+	hex
+	default 0x1080
+	help
+	  GPIO i/o-mapped base address.
+
+config ACPI_GPE0_BASE
+	hex
+	default 0x1100
+	help
+	  ACPI General Purpose Event 0 (GPE0) i/o-mapped base address.
+	  This device is defined in ACPI specification, with 64 bytes in size.
+
+config WDT_BASE
+	hex
+	default 0x1140
+	help
+	  Watchdog timer i/o-mapped base address.
+
+config SYS_CAR_ADDR
+	hex
+	default ESRAM_BASE
+
+config SYS_CAR_SIZE
+	hex
+	default 0x8000
+	help
+	  Space in bytes in eSRAM used as Cache-As-ARM (CAR).
+	  Note this size must not exceed eSRAM's total size.
+
+config TSC_FREQ_IN_MHZ
+	int
+	default 400
+
+endif
diff --git a/arch/x86/cpu/quark/Makefile b/arch/x86/cpu/quark/Makefile
new file mode 100644
index 0000000000..e87b4248e6
--- /dev/null
+++ b/arch/x86/cpu/quark/Makefile
@@ -0,0 +1,9 @@
+#
+# Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+#
+# SPDX-License-Identifier:	GPL-2.0+
+#
+
+obj-y += car.o dram.o msg_port.o quark.o
+obj-y += mrc.o mrc_util.o hte.o smc.o
+obj-$(CONFIG_PCI) += pci.o
diff --git a/arch/x86/cpu/quark/car.S b/arch/x86/cpu/quark/car.S
new file mode 100644
index 0000000000..3432ffa081
--- /dev/null
+++ b/arch/x86/cpu/quark/car.S
@@ -0,0 +1,105 @@
+/*
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <config.h>
+#include <asm/pci.h>
+#include <asm/post.h>
+#include <asm/arch/quark.h>
+#include <asm/arch/msg_port.h>
+
+.globl car_init
+car_init:
+	post_code(POST_CAR_START)
+
+	/*
+	 * Quark SoC contains an embedded 512KiB SRAM (eSRAM) that is
+	 * initialized by hardware. eSRAM is the ideal place to be used
+	 * for Cache-As-RAM (CAR) before system memory is available.
+	 *
+	 * Relocate this eSRAM to a suitable location in the physical
+	 * memory map and enable it.
+	 */
+
+	/* Host Memory Bound Register P03h:R08h */
+	mov	$((MSG_PORT_HOST_BRIDGE << 16) | (HM_BOUND << 8)), %eax
+	mov	$(DRAM_BASE + DRAM_MAX_SIZE + ESRAM_SIZE), %edx
+	lea	1f, %esp
+	jmp	msg_port_write
+1:
+
+	/* eSRAM Block Page Control Register P05h:R82h */
+	mov	$((MSG_PORT_MEM_MGR << 16) | (ESRAM_BLK_CTRL << 8)), %eax
+	mov	$(ESRAM_BLOCK_MODE | (CONFIG_ESRAM_BASE >> 24)), %edx
+	lea	2f, %esp
+	jmp	msg_port_write
+2:
+
+	post_code(POST_CAR_CPU_CACHE)
+	jmp	car_init_ret
+
+msg_port_read:
+	/*
+	 * Parameter:
+	 *   eax[23:16] - Message Port ID
+	 *   eax[15:08] - Register Address
+	 *
+	 * Return Value:
+	 *   eax - Message Port Register value
+	 *
+	 * Return Address: esp
+	 */
+
+	or	$((MSG_OP_READ << 24) | MSG_BYTE_ENABLE), %eax
+	mov	%eax, %ebx
+
+	/* Write MCR B0:D0:F0:RD0 */
+	mov	$(PCI_CFG_EN | MSG_CTRL_REG), %eax
+	mov	$PCI_REG_ADDR, %dx
+	out	%eax, %dx
+	mov	$PCI_REG_DATA, %dx
+	mov	%ebx, %eax
+	out	%eax, %dx
+
+	/* Read MDR B0:D0:F0:RD4 */
+	mov	$(PCI_CFG_EN | MSG_DATA_REG), %eax
+	mov	$PCI_REG_ADDR, %dx
+	out	%eax, %dx
+	mov	$PCI_REG_DATA, %dx
+	in	%dx, %eax
+
+	jmp	*%esp
+
+msg_port_write:
+	/*
+	 * Parameter:
+	 *   eax[23:16] - Message Port ID
+	 *   eax[15:08] - Register Address
+	 *   edx        - Message Port Register value to write
+	 *
+	 * Return Address: esp
+	 */
+
+	or	$((MSG_OP_WRITE << 24) | MSG_BYTE_ENABLE), %eax
+	mov	%eax, %esi
+	mov	%edx, %edi
+
+	/* Write MDR B0:D0:F0:RD4 */
+	mov	$(PCI_CFG_EN | MSG_DATA_REG), %eax
+	mov	$PCI_REG_ADDR, %dx
+	out	%eax, %dx
+	mov	$PCI_REG_DATA, %dx
+	mov	%edi, %eax
+	out	%eax, %dx
+
+	/* Write MCR B0:D0:F0:RD0 */
+	mov	$(PCI_CFG_EN | MSG_CTRL_REG), %eax
+	mov	$PCI_REG_ADDR, %dx
+	out	%eax, %dx
+	mov	$PCI_REG_DATA, %dx
+	mov	%esi, %eax
+	out	%eax, %dx
+
+	jmp	*%esp
diff --git a/arch/x86/cpu/quark/dram.c b/arch/x86/cpu/quark/dram.c
new file mode 100644
index 0000000000..9cac846c69
--- /dev/null
+++ b/arch/x86/cpu/quark/dram.c
@@ -0,0 +1,134 @@
+/*
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <errno.h>
+#include <fdtdec.h>
+#include <asm/post.h>
+#include <asm/arch/mrc.h>
+#include <asm/arch/quark.h>
+
+DECLARE_GLOBAL_DATA_PTR;
+
+static int mrc_configure_params(struct mrc_params *mrc_params)
+{
+	const void *blob = gd->fdt_blob;
+	int node;
+	int mrc_flags;
+
+	node = fdtdec_next_compatible(blob, 0, COMPAT_INTEL_QRK_MRC);
+	if (node < 0) {
+		debug("%s: Cannot find MRC node\n", __func__);
+		return -EINVAL;
+	}
+
+	/*
+	 * TODO:
+	 *
+	 * We need support fast boot (MRC cache) in the future.
+	 *
+	 * Set boot mode to cold boot for now
+	 */
+	mrc_params->boot_mode = BM_COLD;
+
+	/*
+	 * TODO:
+	 *
+	 * We need determine ECC by pin strap state
+	 *
+	 * Disable ECC by default for now
+	 */
+	mrc_params->ecc_enables = 0;
+
+	mrc_flags = fdtdec_get_int(blob, node, "flags", 0);
+	if (mrc_flags & MRC_FLAG_SCRAMBLE_EN)
+		mrc_params->scrambling_enables = 1;
+	else
+		mrc_params->scrambling_enables = 0;
+
+	mrc_params->dram_width = fdtdec_get_int(blob, node, "dram-width", 0);
+	mrc_params->ddr_speed = fdtdec_get_int(blob, node, "dram-speed", 0);
+	mrc_params->ddr_type = fdtdec_get_int(blob, node, "dram-type", 0);
+
+	mrc_params->rank_enables = fdtdec_get_int(blob, node, "rank-mask", 0);
+	mrc_params->channel_enables = fdtdec_get_int(blob, node,
+		"chan-mask", 0);
+	mrc_params->channel_width = fdtdec_get_int(blob, node,
+		"chan-width", 0);
+	mrc_params->address_mode = fdtdec_get_int(blob, node, "addr-mode", 0);
+
+	mrc_params->refresh_rate = fdtdec_get_int(blob, node,
+		"refresh-rate", 0);
+	mrc_params->sr_temp_range = fdtdec_get_int(blob, node,
+		"sr-temp-range", 0);
+	mrc_params->ron_value = fdtdec_get_int(blob, node,
+		"ron-value", 0);
+	mrc_params->rtt_nom_value = fdtdec_get_int(blob, node,
+		"rtt-nom-value", 0);
+	mrc_params->rd_odt_value = fdtdec_get_int(blob, node,
+		"rd-odt-value", 0);
+
+	mrc_params->params.density = fdtdec_get_int(blob, node,
+		"dram-density", 0);
+	mrc_params->params.cl = fdtdec_get_int(blob, node, "dram-cl", 0);
+	mrc_params->params.ras = fdtdec_get_int(blob, node, "dram-ras", 0);
+	mrc_params->params.wtr = fdtdec_get_int(blob, node, "dram-wtr", 0);
+	mrc_params->params.rrd = fdtdec_get_int(blob, node, "dram-rrd", 0);
+	mrc_params->params.faw = fdtdec_get_int(blob, node, "dram-faw", 0);
+
+	debug("MRC dram_width %d\n", mrc_params->dram_width);
+	debug("MRC rank_enables %d\n", mrc_params->rank_enables);
+	debug("MRC ddr_speed %d\n", mrc_params->ddr_speed);
+	debug("MRC flags: %s\n",
+	      (mrc_params->scrambling_enables) ? "SCRAMBLE_EN" : "");
+
+	debug("MRC density=%d tCL=%d tRAS=%d tWTR=%d tRRD=%d tFAW=%d\n",
+	      mrc_params->params.density, mrc_params->params.cl,
+	      mrc_params->params.ras, mrc_params->params.wtr,
+	      mrc_params->params.rrd, mrc_params->params.faw);
+
+	return 0;
+}
+
+int dram_init(void)
+{
+	struct mrc_params mrc_params;
+	int ret;
+
+	memset(&mrc_params, 0, sizeof(struct mrc_params));
+	ret = mrc_configure_params(&mrc_params);
+	if (ret)
+		return ret;
+
+	/* Set up the DRAM by calling the memory reference code */
+	mrc_init(&mrc_params);
+	if (mrc_params.status)
+		return -EIO;
+
+	gd->ram_size = mrc_params.mem_size;
+	post_code(POST_DRAM);
+
+	return 0;
+}
+
+void dram_init_banksize(void)
+{
+	gd->bd->bi_dram[0].start = 0;
+	gd->bd->bi_dram[0].size = gd->ram_size;
+}
+
+/*
+ * This function looks for the highest region of memory lower than 4GB which
+ * has enough space for U-Boot where U-Boot is aligned on a page boundary.
+ * It overrides the default implementation found elsewhere which simply
+ * picks the end of ram, wherever that may be. The location of the stack,
+ * the relocation address, and how far U-Boot is moved by relocation are
+ * set in the global data structure.
+ */
+ulong board_get_usable_ram_top(ulong total_size)
+{
+	return gd->ram_size;
+}
diff --git a/arch/x86/cpu/quark/hte.c b/arch/x86/cpu/quark/hte.c
new file mode 100644
index 0000000000..372815d8c1
--- /dev/null
+++ b/arch/x86/cpu/quark/hte.c
@@ -0,0 +1,396 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * Ported from Intel released Quark UEFI BIOS
+ * QuarkSocPkg/QuarkNorthCluster/MemoryInit/Pei
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+#include <common.h>
+#include <asm/arch/mrc.h>
+#include <asm/arch/msg_port.h>
+#include "mrc_util.h"
+#include "hte.h"
+
+/**
+ * Enable HTE to detect all possible errors for the given training parameters
+ * (per-bit or full byte lane).
+ */
+static void hte_enable_all_errors(void)
+{
+	msg_port_write(HTE, 0x000200A2, 0xFFFFFFFF);
+	msg_port_write(HTE, 0x000200A3, 0x000000FF);
+	msg_port_write(HTE, 0x000200A4, 0x00000000);
+}
+
+/**
+ * Go and read the HTE register in order to find any error
+ *
+ * @return: The errors detected in the HTE status register
+ */
+static u32 hte_check_errors(void)
+{
+	return msg_port_read(HTE, 0x000200A7);
+}
+
+/**
+ * Wait until HTE finishes
+ */
+static void hte_wait_for_complete(void)
+{
+	u32 tmp;
+
+	ENTERFN();
+
+	do {} while ((msg_port_read(HTE, 0x00020012) & BIT30) != 0);
+
+	tmp = msg_port_read(HTE, 0x00020011);
+	tmp |= BIT9;
+	tmp &= ~(BIT12 | BIT13);
+	msg_port_write(HTE, 0x00020011, tmp);
+
+	LEAVEFN();
+}
+
+/**
+ * Clear registers related with errors in the HTE
+ */
+static void hte_clear_error_regs(void)
+{
+	u32 tmp;
+
+	/*
+	 * Clear all HTE errors and enable error checking
+	 * for burst and chunk.
+	 */
+	tmp = msg_port_read(HTE, 0x000200A1);
+	tmp |= BIT8;
+	msg_port_write(HTE, 0x000200A1, tmp);
+}
+
+/**
+ * Execute a basic single-cache-line memory write/read/verify test using simple
+ * constant pattern, different for READ_TRAIN and WRITE_TRAIN modes.
+ *
+ * See hte_basic_write_read() which is the external visible wrapper.
+ *
+ * @mrc_params: host structure for all MRC global data
+ * @addr: memory adress being tested (must hit specific channel/rank)
+ * @first_run: if set then the HTE registers are configured, otherwise it is
+ *             assumed configuration is done and we just re-run the test
+ * @mode: READ_TRAIN or WRITE_TRAIN (the difference is in the pattern)
+ *
+ * @return: byte lane failure on each bit (for Quark only bit0 and bit1)
+ */
+static u16 hte_basic_data_cmp(struct mrc_params *mrc_params, u32 addr,
+			      u8 first_run, u8 mode)
+{
+	u32 pattern;
+	u32 offset;
+
+	if (first_run) {
+		msg_port_write(HTE, 0x00020020, 0x01B10021);
+		msg_port_write(HTE, 0x00020021, 0x06000000);
+		msg_port_write(HTE, 0x00020022, addr >> 6);
+		msg_port_write(HTE, 0x00020062, 0x00800015);
+		msg_port_write(HTE, 0x00020063, 0xAAAAAAAA);
+		msg_port_write(HTE, 0x00020064, 0xCCCCCCCC);
+		msg_port_write(HTE, 0x00020065, 0xF0F0F0F0);
+		msg_port_write(HTE, 0x00020061, 0x00030008);
+
+		if (mode == WRITE_TRAIN)
+			pattern = 0xC33C0000;
+		else /* READ_TRAIN */
+			pattern = 0xAA5555AA;
+
+		for (offset = 0x80; offset <= 0x8F; offset++)
+			msg_port_write(HTE, offset, pattern);
+	}
+
+	msg_port_write(HTE, 0x000200A1, 0xFFFF1000);
+	msg_port_write(HTE, 0x00020011, 0x00011000);
+	msg_port_write(HTE, 0x00020011, 0x00011100);
+
+	hte_wait_for_complete();
+
+	/*
+	 * Return bits 15:8 of HTE_CH0_ERR_XSTAT to check for
+	 * any bytelane errors.
+	 */
+	return (hte_check_errors() >> 8) & 0xFF;
+}
+
+/**
+ * Examine a single-cache-line memory with write/read/verify test using multiple
+ * data patterns (victim-aggressor algorithm).
+ *
+ * See hte_write_stress_bit_lanes() which is the external visible wrapper.
+ *
+ * @mrc_params: host structure for all MRC global data
+ * @addr: memory adress being tested (must hit specific channel/rank)
+ * @loop_cnt: number of test iterations
+ * @seed_victim: victim data pattern seed
+ * @seed_aggressor: aggressor data pattern seed
+ * @victim_bit: should be 0 as auto-rotate feature is in use
+ * @first_run: if set then the HTE registers are configured, otherwise it is
+ *             assumed configuration is done and we just re-run the test
+ *
+ * @return: byte lane failure on each bit (for Quark only bit0 and bit1)
+ */
+static u16 hte_rw_data_cmp(struct mrc_params *mrc_params, u32 addr,
+			   u8 loop_cnt, u32 seed_victim, u32 seed_aggressor,
+			   u8 victim_bit, u8 first_run)
+{
+	u32 offset;
+	u32 tmp;
+
+	if (first_run) {
+		msg_port_write(HTE, 0x00020020, 0x00910024);
+		msg_port_write(HTE, 0x00020023, 0x00810024);
+		msg_port_write(HTE, 0x00020021, 0x06070000);
+		msg_port_write(HTE, 0x00020024, 0x06070000);
+		msg_port_write(HTE, 0x00020022, addr >> 6);
+		msg_port_write(HTE, 0x00020025, addr >> 6);
+		msg_port_write(HTE, 0x00020062, 0x0000002A);
+		msg_port_write(HTE, 0x00020063, seed_victim);
+		msg_port_write(HTE, 0x00020064, seed_aggressor);
+		msg_port_write(HTE, 0x00020065, seed_victim);
+
+		/*
+		 * Write the pattern buffers to select the victim bit
+		 *
+		 * Start with bit0
+		 */
+		for (offset = 0x80; offset <= 0x8F; offset++) {
+			if ((offset % 8) == victim_bit)
+				msg_port_write(HTE, offset, 0x55555555);
+			else
+				msg_port_write(HTE, offset, 0xCCCCCCCC);
+		}
+
+		msg_port_write(HTE, 0x00020061, 0x00000000);
+		msg_port_write(HTE, 0x00020066, 0x03440000);
+		msg_port_write(HTE, 0x000200A1, 0xFFFF1000);
+	}
+
+	tmp = 0x10001000 | (loop_cnt << 16);
+	msg_port_write(HTE, 0x00020011, tmp);
+	msg_port_write(HTE, 0x00020011, tmp | BIT8);
+
+	hte_wait_for_complete();
+
+	/*
+	 * Return bits 15:8 of HTE_CH0_ERR_XSTAT to check for
+	 * any bytelane errors.
+	 */
+	return (hte_check_errors() >> 8) & 0xFF;
+}
+
+/**
+ * Use HW HTE engine to initialize or test all memory attached to a given DUNIT.
+ * If flag is MRC_MEM_INIT, this routine writes 0s to all memory locations to
+ * initialize ECC. If flag is MRC_MEM_TEST, this routine will send an 5AA55AA5
+ * pattern to all memory locations on the RankMask and then read it back.
+ * Then it sends an A55AA55A pattern to all memory locations on the RankMask
+ * and reads it back.
+ *
+ * @mrc_params: host structure for all MRC global data
+ * @flag: MRC_MEM_INIT or MRC_MEM_TEST
+ *
+ * @return: errors register showing HTE failures. Also prints out which rank
+ *          failed the HTE test if failure occurs. For rank detection to work,
+ *          the address map must be left in its default state. If MRC changes
+ *          the address map, this function must be modified to change it back
+ *          to default at the beginning, then restore it at the end.
+ */
+u32 hte_mem_init(struct mrc_params *mrc_params, u8 flag)
+{
+	u32 offset;
+	int test_num;
+	int i;
+
+	/*
+	 * Clear out the error registers at the start of each memory
+	 * init or memory test run.
+	 */
+	hte_clear_error_regs();
+
+	msg_port_write(HTE, 0x00020062, 0x00000015);
+
+	for (offset = 0x80; offset <= 0x8F; offset++)
+		msg_port_write(HTE, offset, ((offset & 1) ? 0xA55A : 0x5AA5));
+
+	msg_port_write(HTE, 0x00020021, 0x00000000);
+	msg_port_write(HTE, 0x00020022, (mrc_params->mem_size >> 6) - 1);
+	msg_port_write(HTE, 0x00020063, 0xAAAAAAAA);
+	msg_port_write(HTE, 0x00020064, 0xCCCCCCCC);
+	msg_port_write(HTE, 0x00020065, 0xF0F0F0F0);
+	msg_port_write(HTE, 0x00020066, 0x03000000);
+
+	switch (flag) {
+	case MRC_MEM_INIT:
+		/*
+		 * Only 1 write pass through memory is needed
+		 * to initialize ECC
+		 */
+		test_num = 1;
+		break;
+	case MRC_MEM_TEST:
+		/* Write/read then write/read with inverted pattern */
+		test_num = 4;
+		break;
+	default:
+		DPF(D_INFO, "Unknown parameter for flag: %d\n", flag);
+		return 0xFFFFFFFF;
+	}
+
+	DPF(D_INFO, "hte_mem_init");
+
+	for (i = 0; i < test_num; i++) {
+		DPF(D_INFO, ".");
+
+		if (i == 0) {
+			msg_port_write(HTE, 0x00020061, 0x00000000);
+			msg_port_write(HTE, 0x00020020, 0x00110010);
+		} else if (i == 1) {
+			msg_port_write(HTE, 0x00020061, 0x00000000);
+			msg_port_write(HTE, 0x00020020, 0x00010010);
+		} else if (i == 2) {
+			msg_port_write(HTE, 0x00020061, 0x00010100);
+			msg_port_write(HTE, 0x00020020, 0x00110010);
+		} else {
+			msg_port_write(HTE, 0x00020061, 0x00010100);
+			msg_port_write(HTE, 0x00020020, 0x00010010);
+		}
+
+		msg_port_write(HTE, 0x00020011, 0x00111000);
+		msg_port_write(HTE, 0x00020011, 0x00111100);
+
+		hte_wait_for_complete();
+
+		/* If this is a READ pass, check for errors at the end */
+		if ((i % 2) == 1) {
+			/* Return immediately if error */
+			if (hte_check_errors())
+				break;
+		}
+	}
+
+	DPF(D_INFO, "done\n");
+
+	return hte_check_errors();
+}
+
+/**
+ * Execute a basic single-cache-line memory write/read/verify test using simple
+ * constant pattern, different for READ_TRAIN and WRITE_TRAIN modes.
+ *
+ * @mrc_params: host structure for all MRC global data
+ * @addr: memory adress being tested (must hit specific channel/rank)
+ * @first_run: if set then the HTE registers are configured, otherwise it is
+ *             assumed configuration is done and we just re-run the test
+ * @mode: READ_TRAIN or WRITE_TRAIN (the difference is in the pattern)
+ *
+ * @return: byte lane failure on each bit (for Quark only bit0 and bit1)
+ */
+u16 hte_basic_write_read(struct mrc_params *mrc_params, u32 addr,
+			 u8 first_run, u8 mode)
+{
+	u16 errors;
+
+	ENTERFN();
+
+	/* Enable all error reporting in preparation for HTE test */
+	hte_enable_all_errors();
+	hte_clear_error_regs();
+
+	errors = hte_basic_data_cmp(mrc_params, addr, first_run, mode);
+
+	LEAVEFN();
+
+	return errors;
+}
+
+/**
+ * Examine a single-cache-line memory with write/read/verify test using multiple
+ * data patterns (victim-aggressor algorithm).
+ *
+ * @mrc_params: host structure for all MRC global data
+ * @addr: memory adress being tested (must hit specific channel/rank)
+ * @first_run: if set then the HTE registers are configured, otherwise it is
+ *             assumed configuration is done and we just re-run the test
+ *
+ * @return: byte lane failure on each bit (for Quark only bit0 and bit1)
+ */
+u16 hte_write_stress_bit_lanes(struct mrc_params *mrc_params,
+			       u32 addr, u8 first_run)
+{
+	u16 errors;
+	u8 victim_bit = 0;
+
+	ENTERFN();
+
+	/* Enable all error reporting in preparation for HTE test */
+	hte_enable_all_errors();
+	hte_clear_error_regs();
+
+	/*
+	 * Loop through each bit in the bytelane.
+	 *
+	 * Each pass creates a victim bit while keeping all other bits the same
+	 * as aggressors. AVN HTE adds an auto-rotate feature which allows us
+	 * to program the entire victim/aggressor sequence in 1 step.
+	 *
+	 * The victim bit rotates on each pass so no need to have software
+	 * implement a victim bit loop like on VLV.
+	 */
+	errors = hte_rw_data_cmp(mrc_params, addr, HTE_LOOP_CNT,
+				 HTE_LFSR_VICTIM_SEED, HTE_LFSR_AGRESSOR_SEED,
+				 victim_bit, first_run);
+
+	LEAVEFN();
+
+	return errors;
+}
+
+/**
+ * Execute a basic single-cache-line memory write or read.
+ * This is just for receive enable / fine write-levelling purpose.
+ *
+ * @addr: memory adress being tested (must hit specific channel/rank)
+ * @first_run: if set then the HTE registers are configured, otherwise it is
+ *             assumed configuration is done and we just re-run the test
+ * @is_write: when non-zero memory write operation executed, otherwise read
+ */
+void hte_mem_op(u32 addr, u8 first_run, u8 is_write)
+{
+	u32 offset;
+	u32 tmp;
+
+	hte_enable_all_errors();
+	hte_clear_error_regs();
+
+	if (first_run) {
+		tmp = is_write ? 0x01110021 : 0x01010021;
+		msg_port_write(HTE, 0x00020020, tmp);
+
+		msg_port_write(HTE, 0x00020021, 0x06000000);
+		msg_port_write(HTE, 0x00020022, addr >> 6);
+		msg_port_write(HTE, 0x00020062, 0x00800015);
+		msg_port_write(HTE, 0x00020063, 0xAAAAAAAA);
+		msg_port_write(HTE, 0x00020064, 0xCCCCCCCC);
+		msg_port_write(HTE, 0x00020065, 0xF0F0F0F0);
+		msg_port_write(HTE, 0x00020061, 0x00030008);
+
+		for (offset = 0x80; offset <= 0x8F; offset++)
+			msg_port_write(HTE, offset, 0xC33C0000);
+	}
+
+	msg_port_write(HTE, 0x000200A1, 0xFFFF1000);
+	msg_port_write(HTE, 0x00020011, 0x00011000);
+	msg_port_write(HTE, 0x00020011, 0x00011100);
+
+	hte_wait_for_complete();
+}
diff --git a/arch/x86/cpu/quark/hte.h b/arch/x86/cpu/quark/hte.h
new file mode 100644
index 0000000000..6577796fd6
--- /dev/null
+++ b/arch/x86/cpu/quark/hte.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * Ported from Intel released Quark UEFI BIOS
+ * QuarkSocPkg/QuarkNorthCluster/MemoryInit/Pei
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+#ifndef _HTE_H_
+#define _HTE_H_
+
+enum {
+	MRC_MEM_INIT,
+	MRC_MEM_TEST
+};
+
+enum {
+	READ_TRAIN,
+	WRITE_TRAIN
+};
+
+/*
+ * EXP_LOOP_CNT field of HTE_CMD_CTL
+ *
+ * This CANNOT be less than 4!
+ */
+#define HTE_LOOP_CNT		5
+
+/* random seed for victim */
+#define HTE_LFSR_VICTIM_SEED	0xF294BA21
+
+/* random seed for aggressor */
+#define HTE_LFSR_AGRESSOR_SEED	0xEBA7492D
+
+u32 hte_mem_init(struct mrc_params *mrc_params, u8 flag);
+u16 hte_basic_write_read(struct mrc_params *mrc_params, u32 addr,
+			 u8 first_run, u8 mode);
+u16 hte_write_stress_bit_lanes(struct mrc_params *mrc_params,
+			       u32 addr, u8 first_run);
+void hte_mem_op(u32 addr, u8 first_run, u8 is_write);
+
+#endif /* _HTE_H_ */
diff --git a/arch/x86/cpu/quark/mrc.c b/arch/x86/cpu/quark/mrc.c
new file mode 100644
index 0000000000..7eb34c5302
--- /dev/null
+++ b/arch/x86/cpu/quark/mrc.c
@@ -0,0 +1,204 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * Ported from Intel released Quark UEFI BIOS
+ * QuarkSocPkg/QuarkNorthCluster/MemoryInit/Pei
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+/*
+ * This is the main Quark Memory Reference Code (MRC)
+ *
+ * These functions are generic and should work for any Quark-based board.
+ *
+ * MRC requires two data structures to be passed in which are initialized by
+ * mrc_adjust_params().
+ *
+ * The basic flow is as follows:
+ * 01) Check for supported DDR speed configuration
+ * 02) Set up Memory Manager buffer as pass-through (POR)
+ * 03) Set Channel Interleaving Mode and Channel Stride to the most aggressive
+ *     setting possible
+ * 04) Set up the Memory Controller logic
+ * 05) Set up the DDR_PHY logic
+ * 06) Initialise the DRAMs (JEDEC)
+ * 07) Perform the Receive Enable Calibration algorithm
+ * 08) Perform the Write Leveling algorithm
+ * 09) Perform the Read Training algorithm (includes internal Vref)
+ * 10) Perform the Write Training algorithm
+ * 11) Set Channel Interleaving Mode and Channel Stride to the desired settings
+ *
+ * DRAM unit configuration based on Valleyview MRC.
+ */
+
+#include <common.h>
+#include <asm/arch/mrc.h>
+#include <asm/arch/msg_port.h>
+#include "mrc_util.h"
+#include "smc.h"
+
+static const struct mem_init init[] = {
+	{ 0x0101, BM_COLD | BM_FAST | BM_WARM | BM_S3, clear_self_refresh       },
+	{ 0x0200, BM_COLD | BM_FAST | BM_WARM | BM_S3, prog_ddr_timing_control  },
+	{ 0x0103, BM_COLD | BM_FAST                  , prog_decode_before_jedec },
+	{ 0x0104, BM_COLD | BM_FAST                  , perform_ddr_reset        },
+	{ 0x0300, BM_COLD | BM_FAST           | BM_S3, ddrphy_init              },
+	{ 0x0400, BM_COLD | BM_FAST                  , perform_jedec_init       },
+	{ 0x0105, BM_COLD | BM_FAST                  , set_ddr_init_complete    },
+	{ 0x0106,           BM_FAST | BM_WARM | BM_S3, restore_timings          },
+	{ 0x0106, BM_COLD                            , default_timings          },
+	{ 0x0500, BM_COLD                            , rcvn_cal                 },
+	{ 0x0600, BM_COLD                            , wr_level                 },
+	{ 0x0120, BM_COLD                            , prog_page_ctrl           },
+	{ 0x0700, BM_COLD                            , rd_train                 },
+	{ 0x0800, BM_COLD                            , wr_train                 },
+	{ 0x010b, BM_COLD                            , store_timings            },
+	{ 0x010c, BM_COLD | BM_FAST | BM_WARM | BM_S3, enable_scrambling        },
+	{ 0x010d, BM_COLD | BM_FAST | BM_WARM | BM_S3, prog_ddr_control         },
+	{ 0x010e, BM_COLD | BM_FAST | BM_WARM | BM_S3, prog_dra_drb             },
+	{ 0x010f,                     BM_WARM | BM_S3, perform_wake             },
+	{ 0x0110, BM_COLD | BM_FAST | BM_WARM | BM_S3, change_refresh_period    },
+	{ 0x0111, BM_COLD | BM_FAST | BM_WARM | BM_S3, set_auto_refresh         },
+	{ 0x0112, BM_COLD | BM_FAST | BM_WARM | BM_S3, ecc_enable               },
+	{ 0x0113, BM_COLD | BM_FAST                  , memory_test              },
+	{ 0x0114, BM_COLD | BM_FAST | BM_WARM | BM_S3, lock_registers           }
+};
+
+/* Adjust configuration parameters before initialization sequence */
+static void mrc_adjust_params(struct mrc_params *mrc_params)
+{
+	const struct dram_params *dram_params;
+	uint8_t dram_width;
+	uint32_t rank_enables;
+	uint32_t channel_width;
+
+	ENTERFN();
+
+	/* initially expect success */
+	mrc_params->status = MRC_SUCCESS;
+
+	dram_width = mrc_params->dram_width;
+	rank_enables = mrc_params->rank_enables;
+	channel_width = mrc_params->channel_width;
+
+	/*
+	 * Setup board layout (must be reviewed as is selecting static timings)
+	 * 0 == R0 (DDR3 x16), 1 == R1 (DDR3 x16),
+	 * 2 == DV (DDR3 x8), 3 == SV (DDR3 x8).
+	 */
+	if (dram_width == X8)
+		mrc_params->board_id = 2;	/* select x8 layout */
+	else
+		mrc_params->board_id = 0;	/* select x16 layout */
+
+	/* initially no memory */
+	mrc_params->mem_size = 0;
+
+	/* begin of channel settings */
+	dram_params = &mrc_params->params;
+
+	/*
+	 * Determine column bits:
+	 *
+	 * Column: 11 for 8Gbx8, else 10
+	 */
+	mrc_params->column_bits[0] =
+		((dram_params[0].density == 4) &&
+		(dram_width == X8)) ? (11) : (10);
+
+	/*
+	 * Determine row bits:
+	 *
+	 * 512Mbx16=12 512Mbx8=13
+	 * 1Gbx16=13   1Gbx8=14
+	 * 2Gbx16=14   2Gbx8=15
+	 * 4Gbx16=15   4Gbx8=16
+	 * 8Gbx16=16   8Gbx8=16
+	 */
+	mrc_params->row_bits[0] = 12 + (dram_params[0].density) +
+		(((dram_params[0].density < 4) &&
+		(dram_width == X8)) ? (1) : (0));
+
+	/*
+	 * Determine per-channel memory size:
+	 *
+	 * (For 2 RANKs, multiply by 2)
+	 * (For 16 bit data bus, divide by 2)
+	 *
+	 * DENSITY WIDTH MEM_AVAILABLE
+	 * 512Mb   x16   0x008000000 ( 128MB)
+	 * 512Mb   x8    0x010000000 ( 256MB)
+	 * 1Gb     x16   0x010000000 ( 256MB)
+	 * 1Gb     x8    0x020000000 ( 512MB)
+	 * 2Gb     x16   0x020000000 ( 512MB)
+	 * 2Gb     x8    0x040000000 (1024MB)
+	 * 4Gb     x16   0x040000000 (1024MB)
+	 * 4Gb     x8    0x080000000 (2048MB)
+	 */
+	mrc_params->channel_size[0] = (1 << dram_params[0].density);
+	mrc_params->channel_size[0] *= (dram_width == X8) ? 2 : 1;
+	mrc_params->channel_size[0] *= (rank_enables == 0x3) ? 2 : 1;
+	mrc_params->channel_size[0] *= (channel_width == X16) ? 1 : 2;
+
+	/* Determine memory size (convert number of 64MB/512Mb units) */
+	mrc_params->mem_size += mrc_params->channel_size[0] << 26;
+
+	LEAVEFN();
+}
+
+static void mrc_mem_init(struct mrc_params *mrc_params)
+{
+	int i;
+
+	ENTERFN();
+
+	/* MRC started */
+	mrc_post_code(0x01, 0x00);
+
+	if (mrc_params->boot_mode != BM_COLD) {
+		if (mrc_params->ddr_speed != mrc_params->timings.ddr_speed) {
+			/* full training required as frequency changed */
+			mrc_params->boot_mode = BM_COLD;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(init); i++) {
+		uint64_t my_tsc;
+
+		if (mrc_params->boot_mode & init[i].boot_path) {
+			uint8_t major = init[i].post_code >> 8 & 0xff;
+			uint8_t minor = init[i].post_code >> 0 & 0xff;
+			mrc_post_code(major, minor);
+
+			my_tsc = rdtsc();
+			init[i].init_fn(mrc_params);
+			DPF(D_TIME, "Execution time %llx", rdtsc() - my_tsc);
+		}
+	}
+
+	/* display the timings */
+	print_timings(mrc_params);
+
+	/* MRC complete */
+	mrc_post_code(0x01, 0xff);
+
+	LEAVEFN();
+}
+
+void mrc_init(struct mrc_params *mrc_params)
+{
+	ENTERFN();
+
+	DPF(D_INFO, "MRC Version %04x %s %s\n", MRC_VERSION,
+	    __DATE__, __TIME__);
+
+	/* Set up the data structures used by mrc_mem_init() */
+	mrc_adjust_params(mrc_params);
+
+	/* Initialize system memory */
+	mrc_mem_init(mrc_params);
+
+	LEAVEFN();
+}
diff --git a/arch/x86/cpu/quark/mrc_util.c b/arch/x86/cpu/quark/mrc_util.c
new file mode 100644
index 0000000000..3a79ae551b
--- /dev/null
+++ b/arch/x86/cpu/quark/mrc_util.c
@@ -0,0 +1,1475 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * Ported from Intel released Quark UEFI BIOS
+ * QuarkSocPkg/QuarkNorthCluster/MemoryInit/Pei
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+#include <common.h>
+#include <asm/arch/device.h>
+#include <asm/arch/mrc.h>
+#include <asm/arch/msg_port.h>
+#include "mrc_util.h"
+#include "hte.h"
+#include "smc.h"
+
+static const uint8_t vref_codes[64] = {
+	/* lowest to highest */
+	0x3F, 0x3E, 0x3D, 0x3C, 0x3B, 0x3A, 0x39, 0x38,
+	0x37, 0x36, 0x35, 0x34, 0x33, 0x32, 0x31, 0x30,
+	0x2F, 0x2E, 0x2D, 0x2C, 0x2B, 0x2A, 0x29, 0x28,
+	0x27, 0x26, 0x25, 0x24, 0x23, 0x22, 0x21, 0x20,
+	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+	0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+	0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+	0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F
+};
+
+void mrc_write_mask(u32 unit, u32 addr, u32 data, u32 mask)
+{
+	msg_port_write(unit, addr,
+		       (msg_port_read(unit, addr) & ~(mask)) |
+		       ((data) & (mask)));
+}
+
+void mrc_alt_write_mask(u32 unit, u32 addr, u32 data, u32 mask)
+{
+	msg_port_alt_write(unit, addr,
+			   (msg_port_alt_read(unit, addr) & ~(mask)) |
+			   ((data) & (mask)));
+}
+
+void mrc_post_code(uint8_t major, uint8_t minor)
+{
+	/* send message to UART */
+	DPF(D_INFO, "POST: 0x%01x%02x\n", major, minor);
+
+	/* error check */
+	if (major == 0xee)
+		hang();
+}
+
+/* Delay number of nanoseconds */
+void delay_n(uint32_t ns)
+{
+	/* 1000 MHz clock has 1ns period --> no conversion required */
+	uint64_t final_tsc = rdtsc();
+
+	final_tsc += ((get_tbclk_mhz() * ns) / 1000);
+
+	while (rdtsc() < final_tsc)
+		;
+}
+
+/* Delay number of microseconds */
+void delay_u(uint32_t ms)
+{
+	/* 64-bit math is not an option, just use loops */
+	while (ms--)
+		delay_n(1000);
+}
+
+/* Select Memory Manager as the source for PRI interface */
+void select_mem_mgr(void)
+{
+	u32 dco;
+
+	ENTERFN();
+
+	dco = msg_port_read(MEM_CTLR, DCO);
+	dco &= ~BIT28;
+	msg_port_write(MEM_CTLR, DCO, dco);
+
+	LEAVEFN();
+}
+
+/* Select HTE as the source for PRI interface */
+void select_hte(void)
+{
+	u32 dco;
+
+	ENTERFN();
+
+	dco = msg_port_read(MEM_CTLR, DCO);
+	dco |= BIT28;
+	msg_port_write(MEM_CTLR, DCO, dco);
+
+	LEAVEFN();
+}
+
+/*
+ * Send DRAM command
+ * data should be formated using DCMD_Xxxx macro or emrsXCommand structure
+ */
+void dram_init_command(uint32_t data)
+{
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_DATA_REG, data);
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_EXT_REG, 0);
+	msg_port_setup(MSG_OP_DRAM_INIT, MEM_CTLR, 0);
+
+	DPF(D_REGWR, "WR32 %03X %08X %08X\n", MEM_CTLR, 0, data);
+}
+
+/* Send DRAM wake command using special MCU side-band WAKE opcode */
+void dram_wake_command(void)
+{
+	ENTERFN();
+
+	msg_port_setup(MSG_OP_DRAM_WAKE, MEM_CTLR, 0);
+
+	LEAVEFN();
+}
+
+void training_message(uint8_t channel, uint8_t rank, uint8_t byte_lane)
+{
+	/* send message to UART */
+	DPF(D_INFO, "CH%01X RK%01X BL%01X\n", channel, rank, byte_lane);
+}
+
+/*
+ * This function will program the RCVEN delays
+ *
+ * (currently doesn't comprehend rank)
+ */
+void set_rcvn(uint8_t channel, uint8_t rank,
+	      uint8_t byte_lane, uint32_t pi_count)
+{
+	uint32_t reg;
+	uint32_t msk;
+	uint32_t temp;
+
+	ENTERFN();
+
+	DPF(D_TRN, "Rcvn ch%d rnk%d ln%d : pi=%03X\n",
+	    channel, rank, byte_lane, pi_count);
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * BL0 -> B01PTRCTL0[11:08] (0x0-0xF)
+	 * BL1 -> B01PTRCTL0[23:20] (0x0-0xF)
+	 */
+	reg = B01PTRCTL0 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	msk = (byte_lane & BIT0) ? (BIT23 | BIT22 | BIT21 | BIT20) :
+		(BIT11 | BIT10 | BIT9 | BIT8);
+	temp = (byte_lane & BIT0) ? ((pi_count / HALF_CLK) << 20) :
+		((pi_count / HALF_CLK) << 8);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* Adjust PI_COUNT */
+	pi_count -= ((pi_count / HALF_CLK) & 0xF) * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * BL0 -> B0DLLPICODER0[29:24] (0x00-0x3F)
+	 * BL1 -> B1DLLPICODER0[29:24] (0x00-0x3F)
+	 */
+	reg = (byte_lane & BIT0) ? B1DLLPICODER0 : B0DLLPICODER0;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	msk = (BIT29 | BIT28 | BIT27 | BIT26 | BIT25 | BIT24);
+	temp = pi_count << 24;
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/*
+	 * DEADBAND
+	 * BL0/1 -> B01DBCTL1[08/11] (+1 select)
+	 * BL0/1 -> B01DBCTL1[02/05] (enable)
+	 */
+	reg = B01DBCTL1 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	msk = 0x00;
+	temp = 0x00;
+
+	/* enable */
+	msk |= (byte_lane & BIT0) ? BIT5 : BIT2;
+	if ((pi_count < EARLY_DB) || (pi_count > LATE_DB))
+		temp |= msk;
+
+	/* select */
+	msk |= (byte_lane & BIT0) ? BIT11 : BIT8;
+	if (pi_count < EARLY_DB)
+		temp |= msk;
+
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* error check */
+	if (pi_count > 0x3F) {
+		training_message(channel, rank, byte_lane);
+		mrc_post_code(0xee, 0xe0);
+	}
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the current RCVEN delay on the given
+ * channel, rank, byte_lane as an absolute PI count.
+ *
+ * (currently doesn't comprehend rank)
+ */
+uint32_t get_rcvn(uint8_t channel, uint8_t rank, uint8_t byte_lane)
+{
+	uint32_t reg;
+	uint32_t temp;
+	uint32_t pi_count;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * BL0 -> B01PTRCTL0[11:08] (0x0-0xF)
+	 * BL1 -> B01PTRCTL0[23:20] (0x0-0xF)
+	 */
+	reg = B01PTRCTL0 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= (byte_lane & BIT0) ? 20 : 8;
+	temp &= 0xF;
+
+	/* Adjust PI_COUNT */
+	pi_count = temp * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * BL0 -> B0DLLPICODER0[29:24] (0x00-0x3F)
+	 * BL1 -> B1DLLPICODER0[29:24] (0x00-0x3F)
+	 */
+	reg = (byte_lane & BIT0) ? B1DLLPICODER0 : B0DLLPICODER0;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= 24;
+	temp &= 0x3F;
+
+	/* Adjust PI_COUNT */
+	pi_count += temp;
+
+	LEAVEFN();
+
+	return pi_count;
+}
+
+/*
+ * This function will program the RDQS delays based on an absolute
+ * amount of PIs.
+ *
+ * (currently doesn't comprehend rank)
+ */
+void set_rdqs(uint8_t channel, uint8_t rank,
+	      uint8_t byte_lane, uint32_t pi_count)
+{
+	uint32_t reg;
+	uint32_t msk;
+	uint32_t temp;
+
+	ENTERFN();
+	DPF(D_TRN, "Rdqs ch%d rnk%d ln%d : pi=%03X\n",
+	    channel, rank, byte_lane, pi_count);
+
+	/*
+	 * PI (1/128 MCLK)
+	 * BL0 -> B0RXDQSPICODE[06:00] (0x00-0x47)
+	 * BL1 -> B1RXDQSPICODE[06:00] (0x00-0x47)
+	 */
+	reg = (byte_lane & BIT0) ? B1RXDQSPICODE : B0RXDQSPICODE;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	msk = (BIT6 | BIT5 | BIT4 | BIT3 | BIT2 | BIT1 | BIT0);
+	temp = pi_count << 0;
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* error check (shouldn't go above 0x3F) */
+	if (pi_count > 0x47) {
+		training_message(channel, rank, byte_lane);
+		mrc_post_code(0xee, 0xe1);
+	}
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the current RDQS delay on the given
+ * channel, rank, byte_lane as an absolute PI count.
+ *
+ * (currently doesn't comprehend rank)
+ */
+uint32_t get_rdqs(uint8_t channel, uint8_t rank, uint8_t byte_lane)
+{
+	uint32_t reg;
+	uint32_t temp;
+	uint32_t pi_count;
+
+	ENTERFN();
+
+	/*
+	 * PI (1/128 MCLK)
+	 * BL0 -> B0RXDQSPICODE[06:00] (0x00-0x47)
+	 * BL1 -> B1RXDQSPICODE[06:00] (0x00-0x47)
+	 */
+	reg = (byte_lane & BIT0) ? B1RXDQSPICODE : B0RXDQSPICODE;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	temp = msg_port_alt_read(DDRPHY, reg);
+
+	/* Adjust PI_COUNT */
+	pi_count = temp & 0x7F;
+
+	LEAVEFN();
+
+	return pi_count;
+}
+
+/*
+ * This function will program the WDQS delays based on an absolute
+ * amount of PIs.
+ *
+ * (currently doesn't comprehend rank)
+ */
+void set_wdqs(uint8_t channel, uint8_t rank,
+	      uint8_t byte_lane, uint32_t pi_count)
+{
+	uint32_t reg;
+	uint32_t msk;
+	uint32_t temp;
+
+	ENTERFN();
+
+	DPF(D_TRN, "Wdqs ch%d rnk%d ln%d : pi=%03X\n",
+	    channel, rank, byte_lane, pi_count);
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * BL0 -> B01PTRCTL0[07:04] (0x0-0xF)
+	 * BL1 -> B01PTRCTL0[19:16] (0x0-0xF)
+	 */
+	reg = B01PTRCTL0 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	msk = (byte_lane & BIT0) ? (BIT19 | BIT18 | BIT17 | BIT16) :
+		(BIT7 | BIT6 | BIT5 | BIT4);
+	temp = pi_count / HALF_CLK;
+	temp <<= (byte_lane & BIT0) ? 16 : 4;
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* Adjust PI_COUNT */
+	pi_count -= ((pi_count / HALF_CLK) & 0xF) * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * BL0 -> B0DLLPICODER0[21:16] (0x00-0x3F)
+	 * BL1 -> B1DLLPICODER0[21:16] (0x00-0x3F)
+	 */
+	reg = (byte_lane & BIT0) ? B1DLLPICODER0 : B0DLLPICODER0;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	msk = (BIT21 | BIT20 | BIT19 | BIT18 | BIT17 | BIT16);
+	temp = pi_count << 16;
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/*
+	 * DEADBAND
+	 * BL0/1 -> B01DBCTL1[07/10] (+1 select)
+	 * BL0/1 -> B01DBCTL1[01/04] (enable)
+	 */
+	reg = B01DBCTL1 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	msk = 0x00;
+	temp = 0x00;
+
+	/* enable */
+	msk |= (byte_lane & BIT0) ? BIT4 : BIT1;
+	if ((pi_count < EARLY_DB) || (pi_count > LATE_DB))
+		temp |= msk;
+
+	/* select */
+	msk |= (byte_lane & BIT0) ? BIT10 : BIT7;
+	if (pi_count < EARLY_DB)
+		temp |= msk;
+
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* error check */
+	if (pi_count > 0x3F) {
+		training_message(channel, rank, byte_lane);
+		mrc_post_code(0xee, 0xe2);
+	}
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the amount of WDQS delay on the given
+ * channel, rank, byte_lane as an absolute PI count.
+ *
+ * (currently doesn't comprehend rank)
+ */
+uint32_t get_wdqs(uint8_t channel, uint8_t rank, uint8_t byte_lane)
+{
+	uint32_t reg;
+	uint32_t temp;
+	uint32_t pi_count;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * BL0 -> B01PTRCTL0[07:04] (0x0-0xF)
+	 * BL1 -> B01PTRCTL0[19:16] (0x0-0xF)
+	 */
+	reg = B01PTRCTL0 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= (byte_lane & BIT0) ? 16 : 4;
+	temp &= 0xF;
+
+	/* Adjust PI_COUNT */
+	pi_count = (temp * HALF_CLK);
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * BL0 -> B0DLLPICODER0[21:16] (0x00-0x3F)
+	 * BL1 -> B1DLLPICODER0[21:16] (0x00-0x3F)
+	 */
+	reg = (byte_lane & BIT0) ? B1DLLPICODER0 : B0DLLPICODER0;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= 16;
+	temp &= 0x3F;
+
+	/* Adjust PI_COUNT */
+	pi_count += temp;
+
+	LEAVEFN();
+
+	return pi_count;
+}
+
+/*
+ * This function will program the WDQ delays based on an absolute
+ * number of PIs.
+ *
+ * (currently doesn't comprehend rank)
+ */
+void set_wdq(uint8_t channel, uint8_t rank,
+	     uint8_t byte_lane, uint32_t pi_count)
+{
+	uint32_t reg;
+	uint32_t msk;
+	uint32_t temp;
+
+	ENTERFN();
+
+	DPF(D_TRN, "Wdq ch%d rnk%d ln%d : pi=%03X\n",
+	    channel, rank, byte_lane, pi_count);
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * BL0 -> B01PTRCTL0[03:00] (0x0-0xF)
+	 * BL1 -> B01PTRCTL0[15:12] (0x0-0xF)
+	 */
+	reg = B01PTRCTL0 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	msk = (byte_lane & BIT0) ? (BIT15 | BIT14 | BIT13 | BIT12) :
+		(BIT3 | BIT2 | BIT1 | BIT0);
+	temp = pi_count / HALF_CLK;
+	temp <<= (byte_lane & BIT0) ? 12 : 0;
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* Adjust PI_COUNT */
+	pi_count -= ((pi_count / HALF_CLK) & 0xF) * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * BL0 -> B0DLLPICODER0[13:08] (0x00-0x3F)
+	 * BL1 -> B1DLLPICODER0[13:08] (0x00-0x3F)
+	 */
+	reg = (byte_lane & BIT0) ? B1DLLPICODER0 : B0DLLPICODER0;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	msk = (BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8);
+	temp = pi_count << 8;
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/*
+	 * DEADBAND
+	 * BL0/1 -> B01DBCTL1[06/09] (+1 select)
+	 * BL0/1 -> B01DBCTL1[00/03] (enable)
+	 */
+	reg = B01DBCTL1 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	msk = 0x00;
+	temp = 0x00;
+
+	/* enable */
+	msk |= (byte_lane & BIT0) ? BIT3 : BIT0;
+	if ((pi_count < EARLY_DB) || (pi_count > LATE_DB))
+		temp |= msk;
+
+	/* select */
+	msk |= (byte_lane & BIT0) ? BIT9 : BIT6;
+	if (pi_count < EARLY_DB)
+		temp |= msk;
+
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* error check */
+	if (pi_count > 0x3F) {
+		training_message(channel, rank, byte_lane);
+		mrc_post_code(0xee, 0xe3);
+	}
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the amount of WDQ delay on the given
+ * channel, rank, byte_lane as an absolute PI count.
+ *
+ * (currently doesn't comprehend rank)
+ */
+uint32_t get_wdq(uint8_t channel, uint8_t rank, uint8_t byte_lane)
+{
+	uint32_t reg;
+	uint32_t temp;
+	uint32_t pi_count;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * BL0 -> B01PTRCTL0[03:00] (0x0-0xF)
+	 * BL1 -> B01PTRCTL0[15:12] (0x0-0xF)
+	 */
+	reg = B01PTRCTL0 + ((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= (byte_lane & BIT0) ? (12) : (0);
+	temp &= 0xF;
+
+	/* Adjust PI_COUNT */
+	pi_count = temp * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * BL0 -> B0DLLPICODER0[13:08] (0x00-0x3F)
+	 * BL1 -> B1DLLPICODER0[13:08] (0x00-0x3F)
+	 */
+	reg = (byte_lane & BIT0) ? B1DLLPICODER0 : B0DLLPICODER0;
+	reg += (((byte_lane >> 1) * DDRIODQ_BL_OFFSET) +
+		(channel * DDRIODQ_CH_OFFSET));
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= 8;
+	temp &= 0x3F;
+
+	/* Adjust PI_COUNT */
+	pi_count += temp;
+
+	LEAVEFN();
+
+	return pi_count;
+}
+
+/*
+ * This function will program the WCMD delays based on an absolute
+ * number of PIs.
+ */
+void set_wcmd(uint8_t channel, uint32_t pi_count)
+{
+	uint32_t reg;
+	uint32_t msk;
+	uint32_t temp;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * CMDPTRREG[11:08] (0x0-0xF)
+	 */
+	reg = CMDPTRREG + (channel * DDRIOCCC_CH_OFFSET);
+	msk = (BIT11 | BIT10 | BIT9 | BIT8);
+	temp = pi_count / HALF_CLK;
+	temp <<= 8;
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* Adjust PI_COUNT */
+	pi_count -= ((pi_count / HALF_CLK) & 0xF) * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * CMDDLLPICODER0[29:24] -> CMDSLICE R3 (unused)
+	 * CMDDLLPICODER0[21:16] -> CMDSLICE L3 (unused)
+	 * CMDDLLPICODER0[13:08] -> CMDSLICE R2 (unused)
+	 * CMDDLLPICODER0[05:00] -> CMDSLICE L2 (unused)
+	 * CMDDLLPICODER1[29:24] -> CMDSLICE R1 (unused)
+	 * CMDDLLPICODER1[21:16] -> CMDSLICE L1 (0x00-0x3F)
+	 * CMDDLLPICODER1[13:08] -> CMDSLICE R0 (unused)
+	 * CMDDLLPICODER1[05:00] -> CMDSLICE L0 (unused)
+	 */
+	reg = CMDDLLPICODER1 + (channel * DDRIOCCC_CH_OFFSET);
+
+	msk = (BIT29 | BIT28 | BIT27 | BIT26 | BIT25 | BIT24 |
+		BIT21 | BIT20 | BIT19 | BIT18 | BIT17 | BIT16 |
+		BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8 |
+		BIT5 | BIT4 | BIT3 | BIT2 | BIT1 | BIT0);
+
+	temp = (pi_count << 24) | (pi_count << 16) |
+		(pi_count << 8) | (pi_count << 0);
+
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+	reg = CMDDLLPICODER0 + (channel * DDRIOCCC_CH_OFFSET);	/* PO */
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/*
+	 * DEADBAND
+	 * CMDCFGREG0[17] (+1 select)
+	 * CMDCFGREG0[16] (enable)
+	 */
+	reg = CMDCFGREG0 + (channel * DDRIOCCC_CH_OFFSET);
+	msk = 0x00;
+	temp = 0x00;
+
+	/* enable */
+	msk |= BIT16;
+	if ((pi_count < EARLY_DB) || (pi_count > LATE_DB))
+		temp |= msk;
+
+	/* select */
+	msk |= BIT17;
+	if (pi_count < EARLY_DB)
+		temp |= msk;
+
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* error check */
+	if (pi_count > 0x3F)
+		mrc_post_code(0xee, 0xe4);
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the amount of WCMD delay on the given
+ * channel as an absolute PI count.
+ */
+uint32_t get_wcmd(uint8_t channel)
+{
+	uint32_t reg;
+	uint32_t temp;
+	uint32_t pi_count;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * CMDPTRREG[11:08] (0x0-0xF)
+	 */
+	reg = CMDPTRREG + (channel * DDRIOCCC_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= 8;
+	temp &= 0xF;
+
+	/* Adjust PI_COUNT */
+	pi_count = temp * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * CMDDLLPICODER0[29:24] -> CMDSLICE R3 (unused)
+	 * CMDDLLPICODER0[21:16] -> CMDSLICE L3 (unused)
+	 * CMDDLLPICODER0[13:08] -> CMDSLICE R2 (unused)
+	 * CMDDLLPICODER0[05:00] -> CMDSLICE L2 (unused)
+	 * CMDDLLPICODER1[29:24] -> CMDSLICE R1 (unused)
+	 * CMDDLLPICODER1[21:16] -> CMDSLICE L1 (0x00-0x3F)
+	 * CMDDLLPICODER1[13:08] -> CMDSLICE R0 (unused)
+	 * CMDDLLPICODER1[05:00] -> CMDSLICE L0 (unused)
+	 */
+	reg = CMDDLLPICODER1 + (channel * DDRIOCCC_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= 16;
+	temp &= 0x3F;
+
+	/* Adjust PI_COUNT */
+	pi_count += temp;
+
+	LEAVEFN();
+
+	return pi_count;
+}
+
+/*
+ * This function will program the WCLK delays based on an absolute
+ * number of PIs.
+ */
+void set_wclk(uint8_t channel, uint8_t rank, uint32_t pi_count)
+{
+	uint32_t reg;
+	uint32_t msk;
+	uint32_t temp;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * CCPTRREG[15:12] -> CLK1 (0x0-0xF)
+	 * CCPTRREG[11:08] -> CLK0 (0x0-0xF)
+	 */
+	reg = CCPTRREG + (channel * DDRIOCCC_CH_OFFSET);
+	msk = (BIT15 | BIT14 | BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8);
+	temp = ((pi_count / HALF_CLK) << 12) | ((pi_count / HALF_CLK) << 8);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* Adjust PI_COUNT */
+	pi_count -= ((pi_count / HALF_CLK) & 0xF) * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * ECCB1DLLPICODER0[13:08] -> CLK0 (0x00-0x3F)
+	 * ECCB1DLLPICODER0[21:16] -> CLK1 (0x00-0x3F)
+	 */
+	reg = rank ? ECCB1DLLPICODER0 : ECCB1DLLPICODER0;
+	reg += (channel * DDRIOCCC_CH_OFFSET);
+	msk = (BIT21 | BIT20 | BIT19 | BIT18 | BIT17 | BIT16 |
+		BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8);
+	temp = (pi_count << 16) | (pi_count << 8);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+	reg = rank ? ECCB1DLLPICODER1 : ECCB1DLLPICODER1;
+	reg += (channel * DDRIOCCC_CH_OFFSET);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+	reg = rank ? ECCB1DLLPICODER2 : ECCB1DLLPICODER2;
+	reg += (channel * DDRIOCCC_CH_OFFSET);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+	reg = rank ? ECCB1DLLPICODER3 : ECCB1DLLPICODER3;
+	reg += (channel * DDRIOCCC_CH_OFFSET);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/*
+	 * DEADBAND
+	 * CCCFGREG1[11:08] (+1 select)
+	 * CCCFGREG1[03:00] (enable)
+	 */
+	reg = CCCFGREG1 + (channel * DDRIOCCC_CH_OFFSET);
+	msk = 0x00;
+	temp = 0x00;
+
+	/* enable */
+	msk |= (BIT3 | BIT2 | BIT1 | BIT0);
+	if ((pi_count < EARLY_DB) || (pi_count > LATE_DB))
+		temp |= msk;
+
+	/* select */
+	msk |= (BIT11 | BIT10 | BIT9 | BIT8);
+	if (pi_count < EARLY_DB)
+		temp |= msk;
+
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* error check */
+	if (pi_count > 0x3F)
+		mrc_post_code(0xee, 0xe5);
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the amout of WCLK delay on the given
+ * channel, rank as an absolute PI count.
+ */
+uint32_t get_wclk(uint8_t channel, uint8_t rank)
+{
+	uint32_t reg;
+	uint32_t temp;
+	uint32_t pi_count;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * CCPTRREG[15:12] -> CLK1 (0x0-0xF)
+	 * CCPTRREG[11:08] -> CLK0 (0x0-0xF)
+	 */
+	reg = CCPTRREG + (channel * DDRIOCCC_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= rank ? 12 : 8;
+	temp &= 0xF;
+
+	/* Adjust PI_COUNT */
+	pi_count = temp * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * ECCB1DLLPICODER0[13:08] -> CLK0 (0x00-0x3F)
+	 * ECCB1DLLPICODER0[21:16] -> CLK1 (0x00-0x3F)
+	 */
+	reg = rank ? ECCB1DLLPICODER0 : ECCB1DLLPICODER0;
+	reg += (channel * DDRIOCCC_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= rank ? 16 : 8;
+	temp &= 0x3F;
+
+	pi_count += temp;
+
+	LEAVEFN();
+
+	return pi_count;
+}
+
+/*
+ * This function will program the WCTL delays based on an absolute
+ * number of PIs.
+ *
+ * (currently doesn't comprehend rank)
+ */
+void set_wctl(uint8_t channel, uint8_t rank, uint32_t pi_count)
+{
+	uint32_t reg;
+	uint32_t msk;
+	uint32_t temp;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * CCPTRREG[31:28] (0x0-0xF)
+	 * CCPTRREG[27:24] (0x0-0xF)
+	 */
+	reg = CCPTRREG + (channel * DDRIOCCC_CH_OFFSET);
+	msk = (BIT31 | BIT30 | BIT29 | BIT28 | BIT27 | BIT26 | BIT25 | BIT24);
+	temp = ((pi_count / HALF_CLK) << 28) | ((pi_count / HALF_CLK) << 24);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* Adjust PI_COUNT */
+	pi_count -= ((pi_count / HALF_CLK) & 0xF) * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * ECCB1DLLPICODER?[29:24] (0x00-0x3F)
+	 * ECCB1DLLPICODER?[29:24] (0x00-0x3F)
+	 */
+	reg = ECCB1DLLPICODER0 + (channel * DDRIOCCC_CH_OFFSET);
+	msk = (BIT29 | BIT28 | BIT27 | BIT26 | BIT25 | BIT24);
+	temp = (pi_count << 24);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+	reg = ECCB1DLLPICODER1 + (channel * DDRIOCCC_CH_OFFSET);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+	reg = ECCB1DLLPICODER2 + (channel * DDRIOCCC_CH_OFFSET);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+	reg = ECCB1DLLPICODER3 + (channel * DDRIOCCC_CH_OFFSET);
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/*
+	 * DEADBAND
+	 * CCCFGREG1[13:12] (+1 select)
+	 * CCCFGREG1[05:04] (enable)
+	 */
+	reg = CCCFGREG1 + (channel * DDRIOCCC_CH_OFFSET);
+	msk = 0x00;
+	temp = 0x00;
+
+	/* enable */
+	msk |= (BIT5 | BIT4);
+	if ((pi_count < EARLY_DB) || (pi_count > LATE_DB))
+		temp |= msk;
+
+	/* select */
+	msk |= (BIT13 | BIT12);
+	if (pi_count < EARLY_DB)
+		temp |= msk;
+
+	mrc_alt_write_mask(DDRPHY, reg, temp, msk);
+
+	/* error check */
+	if (pi_count > 0x3F)
+		mrc_post_code(0xee, 0xe6);
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the amount of WCTL delay on the given
+ * channel, rank as an absolute PI count.
+ *
+ * (currently doesn't comprehend rank)
+ */
+uint32_t get_wctl(uint8_t channel, uint8_t rank)
+{
+	uint32_t reg;
+	uint32_t temp;
+	uint32_t pi_count;
+
+	ENTERFN();
+
+	/*
+	 * RDPTR (1/2 MCLK, 64 PIs)
+	 * CCPTRREG[31:28] (0x0-0xF)
+	 * CCPTRREG[27:24] (0x0-0xF)
+	 */
+	reg = CCPTRREG + (channel * DDRIOCCC_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= 24;
+	temp &= 0xF;
+
+	/* Adjust PI_COUNT */
+	pi_count = temp * HALF_CLK;
+
+	/*
+	 * PI (1/64 MCLK, 1 PIs)
+	 * ECCB1DLLPICODER?[29:24] (0x00-0x3F)
+	 * ECCB1DLLPICODER?[29:24] (0x00-0x3F)
+	 */
+	reg = ECCB1DLLPICODER0 + (channel * DDRIOCCC_CH_OFFSET);
+	temp = msg_port_alt_read(DDRPHY, reg);
+	temp >>= 24;
+	temp &= 0x3F;
+
+	/* Adjust PI_COUNT */
+	pi_count += temp;
+
+	LEAVEFN();
+
+	return pi_count;
+}
+
+/*
+ * This function will program the internal Vref setting in a given
+ * byte lane in a given channel.
+ */
+void set_vref(uint8_t channel, uint8_t byte_lane, uint32_t setting)
+{
+	uint32_t reg = (byte_lane & 0x1) ? (B1VREFCTL) : (B0VREFCTL);
+
+	ENTERFN();
+
+	DPF(D_TRN, "Vref ch%d ln%d : val=%03X\n",
+	    channel, byte_lane, setting);
+
+	mrc_alt_write_mask(DDRPHY, (reg + (channel * DDRIODQ_CH_OFFSET) +
+		((byte_lane >> 1) * DDRIODQ_BL_OFFSET)),
+		(vref_codes[setting] << 2),
+		(BIT7 | BIT6 | BIT5 | BIT4 | BIT3 | BIT2));
+
+	/*
+	 * need to wait ~300ns for Vref to settle
+	 * (check that this is necessary)
+	 */
+	delay_n(300);
+
+	/* ??? may need to clear pointers ??? */
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return the internal Vref setting for the given
+ * channel, byte_lane.
+ */
+uint32_t get_vref(uint8_t channel, uint8_t byte_lane)
+{
+	uint8_t j;
+	uint32_t ret_val = sizeof(vref_codes) / 2;
+	uint32_t reg = (byte_lane & 0x1) ? (B1VREFCTL) : (B0VREFCTL);
+	uint32_t temp;
+
+	ENTERFN();
+
+	temp = msg_port_alt_read(DDRPHY, (reg + (channel * DDRIODQ_CH_OFFSET) +
+		((byte_lane >> 1) * DDRIODQ_BL_OFFSET)));
+	temp >>= 2;
+	temp &= 0x3F;
+
+	for (j = 0; j < sizeof(vref_codes); j++) {
+		if (vref_codes[j] == temp) {
+			ret_val = j;
+			break;
+		}
+	}
+
+	LEAVEFN();
+
+	return ret_val;
+}
+
+/*
+ * This function will return a 32-bit address in the desired
+ * channel and rank.
+ */
+uint32_t get_addr(uint8_t channel, uint8_t rank)
+{
+	uint32_t offset = 0x02000000;	/* 32MB */
+
+	/* Begin product specific code */
+	if (channel > 0) {
+		DPF(D_ERROR, "ILLEGAL CHANNEL\n");
+		DEAD_LOOP();
+	}
+
+	if (rank > 1) {
+		DPF(D_ERROR, "ILLEGAL RANK\n");
+		DEAD_LOOP();
+	}
+
+	/* use 256MB lowest density as per DRP == 0x0003 */
+	offset += rank * (256 * 1024 * 1024);
+
+	return offset;
+}
+
+/*
+ * This function will sample the DQTRAINSTS registers in the given
+ * channel/rank SAMPLE_SIZE times looking for a valid '0' or '1'.
+ *
+ * It will return an encoded 32-bit date in which each bit corresponds to
+ * the sampled value on the byte lane.
+ */
+uint32_t sample_dqs(struct mrc_params *mrc_params, uint8_t channel,
+		    uint8_t rank, bool rcvn)
+{
+	uint8_t j;	/* just a counter */
+	uint8_t bl;	/* which BL in the module (always 2 per module) */
+	uint8_t bl_grp;	/* which BL module */
+	/* byte lane divisor */
+	uint8_t bl_divisor = (mrc_params->channel_width == X16) ? 2 : 1;
+	uint32_t msk[2];	/* BLx in module */
+	/* DQTRAINSTS register contents for each sample */
+	uint32_t sampled_val[SAMPLE_SIZE];
+	uint32_t num_0s;	/* tracks the number of '0' samples */
+	uint32_t num_1s;	/* tracks the number of '1' samples */
+	uint32_t ret_val = 0x00;	/* assume all '0' samples */
+	uint32_t address = get_addr(channel, rank);
+
+	/* initialise msk[] */
+	msk[0] = rcvn ? BIT1 : BIT9;	/* BL0 */
+	msk[1] = rcvn ? BIT0 : BIT8;	/* BL1 */
+
+	/* cycle through each byte lane group */
+	for (bl_grp = 0; bl_grp < (NUM_BYTE_LANES / bl_divisor) / 2; bl_grp++) {
+		/* take SAMPLE_SIZE samples */
+		for (j = 0; j < SAMPLE_SIZE; j++) {
+			hte_mem_op(address, mrc_params->first_run,
+				   rcvn ? 0 : 1);
+			mrc_params->first_run = 0;
+
+			/*
+			 * record the contents of the proper
+			 * DQTRAINSTS register
+			 */
+			sampled_val[j] = msg_port_alt_read(DDRPHY,
+				(DQTRAINSTS +
+				(bl_grp * DDRIODQ_BL_OFFSET) +
+				(channel * DDRIODQ_CH_OFFSET)));
+		}
+
+		/*
+		 * look for a majority value (SAMPLE_SIZE / 2) + 1
+		 * on the byte lane and set that value in the corresponding
+		 * ret_val bit
+		 */
+		for (bl = 0; bl < 2; bl++) {
+			num_0s = 0x00;	/* reset '0' tracker for byte lane */
+			num_1s = 0x00;	/* reset '1' tracker for byte lane */
+			for (j = 0; j < SAMPLE_SIZE; j++) {
+				if (sampled_val[j] & msk[bl])
+					num_1s++;
+				else
+					num_0s++;
+			}
+		if (num_1s > num_0s)
+			ret_val |= (1 << (bl + (bl_grp * 2)));
+		}
+	}
+
+	/*
+	 * "ret_val.0" contains the status of BL0
+	 * "ret_val.1" contains the status of BL1
+	 * "ret_val.2" contains the status of BL2
+	 * etc.
+	 */
+	return ret_val;
+}
+
+/* This function will find the rising edge transition on RCVN or WDQS */
+void find_rising_edge(struct mrc_params *mrc_params, uint32_t delay[],
+		      uint8_t channel, uint8_t rank, bool rcvn)
+{
+	bool all_edges_found;	/* determines stop condition */
+	bool direction[NUM_BYTE_LANES];	/* direction indicator */
+	uint8_t sample;	/* sample counter */
+	uint8_t bl;	/* byte lane counter */
+	/* byte lane divisor */
+	uint8_t bl_divisor = (mrc_params->channel_width == X16) ? 2 : 1;
+	uint32_t sample_result[SAMPLE_CNT];	/* results of sample_dqs() */
+	uint32_t temp;
+	uint32_t transition_pattern;
+
+	ENTERFN();
+
+	/* select hte and request initial configuration */
+	select_hte();
+	mrc_params->first_run = 1;
+
+	/* Take 3 sample points (T1,T2,T3) to obtain a transition pattern */
+	for (sample = 0; sample < SAMPLE_CNT; sample++) {
+		/* program the desired delays for sample */
+		for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+			/* increase sample delay by 26 PI (0.2 CLK) */
+			if (rcvn) {
+				set_rcvn(channel, rank, bl,
+					 delay[bl] + (sample * SAMPLE_DLY));
+			} else {
+				set_wdqs(channel, rank, bl,
+					 delay[bl] + (sample * SAMPLE_DLY));
+			}
+		}
+
+		/* take samples (Tsample_i) */
+		sample_result[sample] = sample_dqs(mrc_params,
+			channel, rank, rcvn);
+
+		DPF(D_TRN,
+		    "Find rising edge %s ch%d rnk%d: #%d dly=%d dqs=%02X\n",
+		    (rcvn ? "RCVN" : "WDQS"), channel, rank, sample,
+		    sample * SAMPLE_DLY, sample_result[sample]);
+	}
+
+	/*
+	 * This pattern will help determine where we landed and ultimately
+	 * how to place RCVEN/WDQS.
+	 */
+	for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+		/* build transition_pattern (MSB is 1st sample) */
+		transition_pattern = 0;
+		for (sample = 0; sample < SAMPLE_CNT; sample++) {
+			transition_pattern |=
+				((sample_result[sample] & (1 << bl)) >> bl) <<
+				(SAMPLE_CNT - 1 - sample);
+		}
+
+		DPF(D_TRN, "=== transition pattern %d\n", transition_pattern);
+
+		/*
+		 * set up to look for rising edge based on
+		 * transition_pattern
+		 */
+		switch (transition_pattern) {
+		case 0:	/* sampled 0->0->0 */
+			/* move forward from T3 looking for 0->1 */
+			delay[bl] += 2 * SAMPLE_DLY;
+			direction[bl] = FORWARD;
+			break;
+		case 1:	/* sampled 0->0->1 */
+		case 5:	/* sampled 1->0->1 (bad duty cycle) *HSD#237503* */
+			/* move forward from T2 looking for 0->1 */
+			delay[bl] += 1 * SAMPLE_DLY;
+			direction[bl] = FORWARD;
+			break;
+		case 2:	/* sampled 0->1->0 (bad duty cycle) *HSD#237503* */
+		case 3:	/* sampled 0->1->1 */
+			/* move forward from T1 looking for 0->1 */
+			delay[bl] += 0 * SAMPLE_DLY;
+			direction[bl] = FORWARD;
+			break;
+		case 4:	/* sampled 1->0->0 (assumes BL8, HSD#234975) */
+			/* move forward from T3 looking for 0->1 */
+			delay[bl] += 2 * SAMPLE_DLY;
+			direction[bl] = FORWARD;
+			break;
+		case 6:	/* sampled 1->1->0 */
+		case 7:	/* sampled 1->1->1 */
+			/* move backward from T1 looking for 1->0 */
+			delay[bl] += 0 * SAMPLE_DLY;
+			direction[bl] = BACKWARD;
+			break;
+		default:
+			mrc_post_code(0xee, 0xee);
+			break;
+		}
+
+		/* program delays */
+		if (rcvn)
+			set_rcvn(channel, rank, bl, delay[bl]);
+		else
+			set_wdqs(channel, rank, bl, delay[bl]);
+	}
+
+	/*
+	 * Based on the observed transition pattern on the byte lane,
+	 * begin looking for a rising edge with single PI granularity.
+	 */
+	do {
+		all_edges_found = true;	/* assume all byte lanes passed */
+		/* take a sample */
+		temp = sample_dqs(mrc_params, channel, rank, rcvn);
+		/* check all each byte lane for proper edge */
+		for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+			if (temp & (1 << bl)) {
+				/* sampled "1" */
+				if (direction[bl] == BACKWARD) {
+					/*
+					 * keep looking for edge
+					 * on this byte lane
+					 */
+					all_edges_found = false;
+					delay[bl] -= 1;
+					if (rcvn) {
+						set_rcvn(channel, rank,
+							 bl, delay[bl]);
+					} else {
+						set_wdqs(channel, rank,
+							 bl, delay[bl]);
+					}
+				}
+			} else {
+				/* sampled "0" */
+				if (direction[bl] == FORWARD) {
+					/*
+					 * keep looking for edge
+					 * on this byte lane
+					 */
+					all_edges_found = false;
+					delay[bl] += 1;
+					if (rcvn) {
+						set_rcvn(channel, rank,
+							 bl, delay[bl]);
+					} else {
+						set_wdqs(channel, rank,
+							 bl, delay[bl]);
+					}
+				}
+			}
+		}
+	} while (!all_edges_found);
+
+	/* restore DDR idle state */
+	dram_init_command(DCMD_PREA(rank));
+
+	DPF(D_TRN, "Delay %03X %03X %03X %03X\n",
+	    delay[0], delay[1], delay[2], delay[3]);
+
+	LEAVEFN();
+}
+
+/*
+ * This function will return a 32 bit mask that will be used to
+ * check for byte lane failures.
+ */
+uint32_t byte_lane_mask(struct mrc_params *mrc_params)
+{
+	uint32_t j;
+	uint32_t ret_val = 0x00;
+
+	/*
+	 * set ret_val based on NUM_BYTE_LANES such that you will check
+	 * only BL0 in result
+	 *
+	 * (each bit in result represents a byte lane)
+	 */
+	for (j = 0; j < MAX_BYTE_LANES; j += NUM_BYTE_LANES)
+		ret_val |= (1 << ((j / NUM_BYTE_LANES) * NUM_BYTE_LANES));
+
+	/*
+	 * HSD#235037
+	 * need to adjust the mask for 16-bit mode
+	 */
+	if (mrc_params->channel_width == X16)
+		ret_val |= (ret_val << 2);
+
+	return ret_val;
+}
+
+/*
+ * Check memory executing simple write/read/verify at the specified address.
+ *
+ * Bits in the result indicate failure on specific byte lane.
+ */
+uint32_t check_rw_coarse(struct mrc_params *mrc_params, uint32_t address)
+{
+	uint32_t result = 0;
+	uint8_t first_run = 0;
+
+	if (mrc_params->hte_setup) {
+		mrc_params->hte_setup = 0;
+		first_run = 1;
+		select_hte();
+	}
+
+	result = hte_basic_write_read(mrc_params, address, first_run,
+				      WRITE_TRAIN);
+
+	DPF(D_TRN, "check_rw_coarse result is %x\n", result);
+
+	return result;
+}
+
+/*
+ * Check memory executing write/read/verify of many data patterns
+ * at the specified address. Bits in the result indicate failure
+ * on specific byte lane.
+ */
+uint32_t check_bls_ex(struct mrc_params *mrc_params, uint32_t address)
+{
+	uint32_t result;
+	uint8_t first_run = 0;
+
+	if (mrc_params->hte_setup) {
+		mrc_params->hte_setup = 0;
+		first_run = 1;
+		select_hte();
+	}
+
+	result = hte_write_stress_bit_lanes(mrc_params, address, first_run);
+
+	DPF(D_TRN, "check_bls_ex result is %x\n", result);
+
+	return result;
+}
+
+/*
+ * 32-bit LFSR with characteristic polynomial: X^32 + X^22 +X^2 + X^1
+ *
+ * The function takes pointer to previous 32 bit value and
+ * modifies it to next value.
+ */
+void lfsr32(uint32_t *lfsr_ptr)
+{
+	uint32_t bit;
+	uint32_t lfsr;
+	int i;
+
+	lfsr = *lfsr_ptr;
+
+	for (i = 0; i < 32; i++) {
+		bit = 1 ^ (lfsr & BIT0);
+		bit = bit ^ ((lfsr & BIT1) >> 1);
+		bit = bit ^ ((lfsr & BIT2) >> 2);
+		bit = bit ^ ((lfsr & BIT22) >> 22);
+
+		lfsr = ((lfsr >> 1) | (bit << 31));
+	}
+
+	*lfsr_ptr = lfsr;
+}
+
+/* Clear the pointers in a given byte lane in a given channel */
+void clear_pointers(void)
+{
+	uint8_t channel;
+	uint8_t bl;
+
+	ENTERFN();
+
+	for (channel = 0; channel < NUM_CHANNELS; channel++) {
+		for (bl = 0; bl < NUM_BYTE_LANES; bl++) {
+			mrc_alt_write_mask(DDRPHY,
+					   (B01PTRCTL1 +
+					   (channel * DDRIODQ_CH_OFFSET) +
+					   ((bl >> 1) * DDRIODQ_BL_OFFSET)),
+					   ~BIT8, BIT8);
+
+			mrc_alt_write_mask(DDRPHY,
+					   (B01PTRCTL1 +
+					   (channel * DDRIODQ_CH_OFFSET) +
+					   ((bl >> 1) * DDRIODQ_BL_OFFSET)),
+					   BIT8, BIT8);
+		}
+	}
+
+	LEAVEFN();
+}
+
+static void print_timings_internal(uint8_t algo, uint8_t channel, uint8_t rank,
+				   uint8_t bl_divisor)
+{
+	uint8_t bl;
+
+	switch (algo) {
+	case RCVN:
+		DPF(D_INFO, "\nRCVN[%02d:%02d]", channel, rank);
+		break;
+	case WDQS:
+		DPF(D_INFO, "\nWDQS[%02d:%02d]", channel, rank);
+		break;
+	case WDQX:
+		DPF(D_INFO, "\nWDQx[%02d:%02d]", channel, rank);
+		break;
+	case RDQS:
+		DPF(D_INFO, "\nRDQS[%02d:%02d]", channel, rank);
+		break;
+	case VREF:
+		DPF(D_INFO, "\nVREF[%02d:%02d]", channel, rank);
+		break;
+	case WCMD:
+		DPF(D_INFO, "\nWCMD[%02d:%02d]", channel, rank);
+		break;
+	case WCTL:
+		DPF(D_INFO, "\nWCTL[%02d:%02d]", channel, rank);
+		break;
+	case WCLK:
+		DPF(D_INFO, "\nWCLK[%02d:%02d]", channel, rank);
+		break;
+	default:
+		break;
+	}
+
+	for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+		switch (algo) {
+		case RCVN:
+			DPF(D_INFO, " %03d", get_rcvn(channel, rank, bl));
+			break;
+		case WDQS:
+			DPF(D_INFO, " %03d", get_wdqs(channel, rank, bl));
+			break;
+		case WDQX:
+			DPF(D_INFO, " %03d", get_wdq(channel, rank, bl));
+			break;
+		case RDQS:
+			DPF(D_INFO, " %03d", get_rdqs(channel, rank, bl));
+			break;
+		case VREF:
+			DPF(D_INFO, " %03d", get_vref(channel, bl));
+			break;
+		case WCMD:
+			DPF(D_INFO, " %03d", get_wcmd(channel));
+			break;
+		case WCTL:
+			DPF(D_INFO, " %03d", get_wctl(channel, rank));
+			break;
+		case WCLK:
+			DPF(D_INFO, " %03d", get_wclk(channel, rank));
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+void print_timings(struct mrc_params *mrc_params)
+{
+	uint8_t algo;
+	uint8_t channel;
+	uint8_t rank;
+	uint8_t bl_divisor = (mrc_params->channel_width == X16) ? 2 : 1;
+
+	DPF(D_INFO, "\n---------------------------");
+	DPF(D_INFO, "\nALGO[CH:RK] BL0 BL1 BL2 BL3");
+	DPF(D_INFO, "\n===========================");
+
+	for (algo = 0; algo < MAX_ALGOS; algo++) {
+		for (channel = 0; channel < NUM_CHANNELS; channel++) {
+			if (mrc_params->channel_enables & (1 << channel)) {
+				for (rank = 0; rank < NUM_RANKS; rank++) {
+					if (mrc_params->rank_enables &
+						(1 << rank)) {
+						print_timings_internal(algo,
+							channel, rank,
+							bl_divisor);
+					}
+				}
+			}
+		}
+	}
+
+	DPF(D_INFO, "\n---------------------------");
+	DPF(D_INFO, "\n");
+}
diff --git a/arch/x86/cpu/quark/mrc_util.h b/arch/x86/cpu/quark/mrc_util.h
new file mode 100644
index 0000000000..f0ddbce3c5
--- /dev/null
+++ b/arch/x86/cpu/quark/mrc_util.h
@@ -0,0 +1,153 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * Ported from Intel released Quark UEFI BIOS
+ * QuarkSocPkg/QuarkNorthCluster/MemoryInit/Pei
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+#ifndef _MRC_UTIL_H_
+#define _MRC_UTIL_H_
+
+/* Turn on this macro to enable MRC debugging output */
+#undef  MRC_DEBUG
+
+/* MRC Debug Support */
+#define DPF		debug_cond
+
+/* debug print type */
+
+#ifdef MRC_DEBUG
+#define D_ERROR		0x0001
+#define D_INFO		0x0002
+#define D_REGRD		0x0004
+#define D_REGWR		0x0008
+#define D_FCALL		0x0010
+#define D_TRN		0x0020
+#define D_TIME		0x0040
+#else
+#define D_ERROR		0
+#define D_INFO		0
+#define D_REGRD		0
+#define D_REGWR		0
+#define D_FCALL		0
+#define D_TRN		0
+#define D_TIME		0
+#endif
+
+#define ENTERFN(...)	debug_cond(D_FCALL, "<%s>\n", __func__)
+#define LEAVEFN(...)	debug_cond(D_FCALL, "</%s>\n", __func__)
+#define REPORTFN(...)	debug_cond(D_FCALL, "<%s/>\n", __func__)
+
+/* Generic Register Bits */
+#define BIT0		0x00000001
+#define BIT1		0x00000002
+#define BIT2		0x00000004
+#define BIT3		0x00000008
+#define BIT4		0x00000010
+#define BIT5		0x00000020
+#define BIT6		0x00000040
+#define BIT7		0x00000080
+#define BIT8		0x00000100
+#define BIT9		0x00000200
+#define BIT10		0x00000400
+#define BIT11		0x00000800
+#define BIT12		0x00001000
+#define BIT13		0x00002000
+#define BIT14		0x00004000
+#define BIT15		0x00008000
+#define BIT16		0x00010000
+#define BIT17		0x00020000
+#define BIT18		0x00040000
+#define BIT19		0x00080000
+#define BIT20		0x00100000
+#define BIT21		0x00200000
+#define BIT22		0x00400000
+#define BIT23		0x00800000
+#define BIT24		0x01000000
+#define BIT25		0x02000000
+#define BIT26		0x04000000
+#define BIT27		0x08000000
+#define BIT28		0x10000000
+#define BIT29		0x20000000
+#define BIT30		0x40000000
+#define BIT31		0x80000000
+
+/* Message Bus Port */
+#define MEM_CTLR	0x01
+#define HOST_BRIDGE	0x03
+#define MEM_MGR		0x05
+#define HTE		0x11
+#define DDRPHY		0x12
+
+/* number of sample points */
+#define SAMPLE_CNT	3
+/* number of PIs to increment per sample */
+#define SAMPLE_DLY	26
+
+enum {
+	/* indicates to decrease delays when looking for edge */
+	BACKWARD,
+	/* indicates to increase delays when looking for edge */
+	FORWARD
+};
+
+enum {
+	RCVN,
+	WDQS,
+	WDQX,
+	RDQS,
+	VREF,
+	WCMD,
+	WCTL,
+	WCLK,
+	MAX_ALGOS,
+};
+
+void mrc_write_mask(u32 unit, u32 addr, u32 data, u32 mask);
+void mrc_alt_write_mask(u32 unit, u32 addr, u32 data, u32 mask);
+void mrc_post_code(uint8_t major, uint8_t minor);
+void delay_n(uint32_t ns);
+void delay_u(uint32_t ms);
+void select_mem_mgr(void);
+void select_hte(void);
+void dram_init_command(uint32_t data);
+void dram_wake_command(void);
+void training_message(uint8_t channel, uint8_t rank, uint8_t byte_lane);
+
+void set_rcvn(uint8_t channel, uint8_t rank,
+	      uint8_t byte_lane, uint32_t pi_count);
+uint32_t get_rcvn(uint8_t channel, uint8_t rank, uint8_t byte_lane);
+void set_rdqs(uint8_t channel, uint8_t rank,
+	      uint8_t byte_lane, uint32_t pi_count);
+uint32_t get_rdqs(uint8_t channel, uint8_t rank, uint8_t byte_lane);
+void set_wdqs(uint8_t channel, uint8_t rank,
+	      uint8_t byte_lane, uint32_t pi_count);
+uint32_t get_wdqs(uint8_t channel, uint8_t rank, uint8_t byte_lane);
+void set_wdq(uint8_t channel, uint8_t rank,
+	     uint8_t byte_lane, uint32_t pi_count);
+uint32_t get_wdq(uint8_t channel, uint8_t rank, uint8_t byte_lane);
+void set_wcmd(uint8_t channel, uint32_t pi_count);
+uint32_t get_wcmd(uint8_t channel);
+void set_wclk(uint8_t channel, uint8_t rank, uint32_t pi_count);
+uint32_t get_wclk(uint8_t channel, uint8_t rank);
+void set_wctl(uint8_t channel, uint8_t rank, uint32_t pi_count);
+uint32_t get_wctl(uint8_t channel, uint8_t rank);
+void set_vref(uint8_t channel, uint8_t byte_lane, uint32_t setting);
+uint32_t get_vref(uint8_t channel, uint8_t byte_lane);
+
+uint32_t get_addr(uint8_t channel, uint8_t rank);
+uint32_t sample_dqs(struct mrc_params *mrc_params, uint8_t channel,
+		    uint8_t rank, bool rcvn);
+void find_rising_edge(struct mrc_params *mrc_params, uint32_t delay[],
+		      uint8_t channel, uint8_t rank, bool rcvn);
+uint32_t byte_lane_mask(struct mrc_params *mrc_params);
+uint32_t check_rw_coarse(struct mrc_params *mrc_params, uint32_t address);
+uint32_t check_bls_ex(struct mrc_params *mrc_params, uint32_t address);
+void lfsr32(uint32_t *lfsr_ptr);
+void clear_pointers(void);
+void print_timings(struct mrc_params *mrc_params);
+
+#endif /* _MRC_UTIL_H_ */
diff --git a/arch/x86/cpu/quark/msg_port.c b/arch/x86/cpu/quark/msg_port.c
new file mode 100644
index 0000000000..31713e321f
--- /dev/null
+++ b/arch/x86/cpu/quark/msg_port.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <pci.h>
+#include <asm/arch/device.h>
+#include <asm/arch/msg_port.h>
+
+void msg_port_setup(int op, int port, int reg)
+{
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_REG,
+			       (((op) << 24) | ((port) << 16) |
+			       (((reg) << 8) & 0xff00) | MSG_BYTE_ENABLE));
+}
+
+u32 msg_port_read(u8 port, u32 reg)
+{
+	u32 value;
+
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_EXT_REG,
+			       reg & 0xffffff00);
+	msg_port_setup(MSG_OP_READ, port, reg);
+	pci_read_config_dword(QUARK_HOST_BRIDGE, MSG_DATA_REG, &value);
+
+	return value;
+}
+
+void msg_port_write(u8 port, u32 reg, u32 value)
+{
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_DATA_REG, value);
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_EXT_REG,
+			       reg & 0xffffff00);
+	msg_port_setup(MSG_OP_WRITE, port, reg);
+}
+
+u32 msg_port_alt_read(u8 port, u32 reg)
+{
+	u32 value;
+
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_EXT_REG,
+			       reg & 0xffffff00);
+	msg_port_setup(MSG_OP_ALT_READ, port, reg);
+	pci_read_config_dword(QUARK_HOST_BRIDGE, MSG_DATA_REG, &value);
+
+	return value;
+}
+
+void msg_port_alt_write(u8 port, u32 reg, u32 value)
+{
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_DATA_REG, value);
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_EXT_REG,
+			       reg & 0xffffff00);
+	msg_port_setup(MSG_OP_ALT_WRITE, port, reg);
+}
+
+u32 msg_port_io_read(u8 port, u32 reg)
+{
+	u32 value;
+
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_EXT_REG,
+			       reg & 0xffffff00);
+	msg_port_setup(MSG_OP_IO_READ, port, reg);
+	pci_read_config_dword(QUARK_HOST_BRIDGE, MSG_DATA_REG, &value);
+
+	return value;
+}
+
+void msg_port_io_write(u8 port, u32 reg, u32 value)
+{
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_DATA_REG, value);
+	pci_write_config_dword(QUARK_HOST_BRIDGE, MSG_CTRL_EXT_REG,
+			       reg & 0xffffff00);
+	msg_port_setup(MSG_OP_IO_WRITE, port, reg);
+}
diff --git a/arch/x86/cpu/quark/pci.c b/arch/x86/cpu/quark/pci.c
new file mode 100644
index 0000000000..354e15a990
--- /dev/null
+++ b/arch/x86/cpu/quark/pci.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <pci.h>
+#include <asm/pci.h>
+#include <asm/arch/device.h>
+
+DECLARE_GLOBAL_DATA_PTR;
+
+void board_pci_setup_hose(struct pci_controller *hose)
+{
+	hose->first_busno = 0;
+	hose->last_busno = 0;
+
+	/* PCI memory space */
+	pci_set_region(hose->regions + 0,
+		       CONFIG_PCI_MEM_BUS,
+		       CONFIG_PCI_MEM_PHYS,
+		       CONFIG_PCI_MEM_SIZE,
+		       PCI_REGION_MEM);
+
+	/* PCI IO space */
+	pci_set_region(hose->regions + 1,
+		       CONFIG_PCI_IO_BUS,
+		       CONFIG_PCI_IO_PHYS,
+		       CONFIG_PCI_IO_SIZE,
+		       PCI_REGION_IO);
+
+	pci_set_region(hose->regions + 2,
+		       CONFIG_PCI_PREF_BUS,
+		       CONFIG_PCI_PREF_PHYS,
+		       CONFIG_PCI_PREF_SIZE,
+		       PCI_REGION_PREFETCH);
+
+	pci_set_region(hose->regions + 3,
+		       0,
+		       0,
+		       gd->ram_size,
+		       PCI_REGION_MEM | PCI_REGION_SYS_MEMORY);
+
+	hose->region_count = 4;
+}
+
+int board_pci_post_scan(struct pci_controller *hose)
+{
+	return 0;
+}
+
+int pci_skip_dev(struct pci_controller *hose, pci_dev_t dev)
+{
+	/*
+	 * TODO:
+	 *
+	 * For some unknown reason, the PCI enumeration process hangs
+	 * when it scans to the PCIe root port 0 (D23:F0) & 1 (D23:F1).
+	 *
+	 * For now we just skip these two devices, and this needs to
+	 * be revisited later.
+	 */
+	if (dev == QUARK_HOST_BRIDGE ||
+	    dev == QUARK_PCIE0 || dev == QUARK_PCIE1) {
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/arch/x86/cpu/quark/quark.c b/arch/x86/cpu/quark/quark.c
new file mode 100644
index 0000000000..dccf7ac5f5
--- /dev/null
+++ b/arch/x86/cpu/quark/quark.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <mmc.h>
+#include <asm/io.h>
+#include <asm/pci.h>
+#include <asm/post.h>
+#include <asm/processor.h>
+#include <asm/arch/device.h>
+#include <asm/arch/msg_port.h>
+#include <asm/arch/quark.h>
+
+static struct pci_device_id mmc_supported[] = {
+	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QRK_SDIO },
+};
+
+/*
+ * TODO:
+ *
+ * This whole routine should be removed until we fully convert the ICH SPI
+ * driver to DM and make use of DT to pass the bios control register offset
+ */
+static void unprotect_spi_flash(void)
+{
+	u32 bc;
+
+	bc = pci_read_config32(QUARK_LEGACY_BRIDGE, 0xd8);
+	bc |= 0x1;	/* unprotect the flash */
+	pci_write_config32(QUARK_LEGACY_BRIDGE, 0xd8, bc);
+}
+
+static void quark_setup_bars(void)
+{
+	/* GPIO - D31:F0:R44h */
+	pci_write_config_dword(QUARK_LEGACY_BRIDGE, LB_GBA,
+			       CONFIG_GPIO_BASE | IO_BAR_EN);
+
+	/* ACPI PM1 Block - D31:F0:R48h */
+	pci_write_config_dword(QUARK_LEGACY_BRIDGE, LB_PM1BLK,
+			       CONFIG_ACPI_PM1_BASE | IO_BAR_EN);
+
+	/* GPE0 - D31:F0:R4Ch */
+	pci_write_config_dword(QUARK_LEGACY_BRIDGE, LB_GPE0BLK,
+			       CONFIG_ACPI_GPE0_BASE | IO_BAR_EN);
+
+	/* WDT - D31:F0:R84h */
+	pci_write_config_dword(QUARK_LEGACY_BRIDGE, LB_WDTBA,
+			       CONFIG_WDT_BASE | IO_BAR_EN);
+
+	/* RCBA - D31:F0:RF0h */
+	pci_write_config_dword(QUARK_LEGACY_BRIDGE, LB_RCBA,
+			       CONFIG_RCBA_BASE | MEM_BAR_EN);
+
+	/* ACPI P Block - Msg Port 04:R70h */
+	msg_port_write(MSG_PORT_RMU, PBLK_BA,
+		       CONFIG_ACPI_PBLK_BASE | IO_BAR_EN);
+
+	/* SPI DMA - Msg Port 04:R7Ah */
+	msg_port_write(MSG_PORT_RMU, SPI_DMA_BA,
+		       CONFIG_SPI_DMA_BASE | IO_BAR_EN);
+
+	/* PCIe ECAM */
+	msg_port_write(MSG_PORT_MEM_ARBITER, AEC_CTRL,
+		       CONFIG_PCIE_ECAM_BASE | MEM_BAR_EN);
+	msg_port_write(MSG_PORT_HOST_BRIDGE, HEC_REG,
+		       CONFIG_PCIE_ECAM_BASE | MEM_BAR_EN);
+}
+
+int arch_cpu_init(void)
+{
+	struct pci_controller *hose;
+	int ret;
+
+	post_code(POST_CPU_INIT);
+#ifdef CONFIG_SYS_X86_TSC_TIMER
+	timer_set_base(rdtsc());
+#endif
+
+	ret = x86_cpu_init_f();
+	if (ret)
+		return ret;
+
+	ret = pci_early_init_hose(&hose);
+	if (ret)
+		return ret;
+
+	/*
+	 * Quark SoC has some non-standard BARs (excluding PCI standard BARs)
+	 * which need be initialized with suggested values
+	 */
+	quark_setup_bars();
+
+	unprotect_spi_flash();
+
+	return 0;
+}
+
+int print_cpuinfo(void)
+{
+	post_code(POST_CPU_INFO);
+	return default_print_cpuinfo();
+}
+
+void reset_cpu(ulong addr)
+{
+	/* cold reset */
+	outb(0x08, PORT_RESET);
+}
+
+int cpu_mmc_init(bd_t *bis)
+{
+	return pci_mmc_init("Quark SDHCI", mmc_supported,
+			    ARRAY_SIZE(mmc_supported));
+}
diff --git a/arch/x86/cpu/quark/smc.c b/arch/x86/cpu/quark/smc.c
new file mode 100644
index 0000000000..e34bec4c80
--- /dev/null
+++ b/arch/x86/cpu/quark/smc.c
@@ -0,0 +1,2764 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * Ported from Intel released Quark UEFI BIOS
+ * QuarkSocPkg/QuarkNorthCluster/MemoryInit/Pei
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+#include <common.h>
+#include <pci.h>
+#include <asm/arch/device.h>
+#include <asm/arch/mrc.h>
+#include <asm/arch/msg_port.h>
+#include "mrc_util.h"
+#include "hte.h"
+#include "smc.h"
+
+/* t_rfc values (in picoseconds) per density */
+static const uint32_t t_rfc[5] = {
+	90000,	/* 512Mb */
+	110000,	/* 1Gb */
+	160000,	/* 2Gb */
+	300000,	/* 4Gb */
+	350000,	/* 8Gb */
+};
+
+/* t_ck clock period in picoseconds per speed index 800, 1066, 1333 */
+static const uint32_t t_ck[3] = {
+	2500,
+	1875,
+	1500
+};
+
+/* Global variables */
+static const uint16_t ddr_wclk[] = {193, 158};
+static const uint16_t ddr_wctl[] = {1, 217};
+static const uint16_t ddr_wcmd[] = {1, 220};
+
+#ifdef BACKUP_RCVN
+static const uint16_t ddr_rcvn[] = {129, 498};
+#endif
+
+#ifdef BACKUP_WDQS
+static const uint16_t ddr_wdqs[] = {65, 289};
+#endif
+
+#ifdef BACKUP_RDQS
+static const uint8_t ddr_rdqs[] = {32, 24};
+#endif
+
+#ifdef BACKUP_WDQ
+static const uint16_t ddr_wdq[] = {32, 257};
+#endif
+
+/* Stop self refresh driven by MCU */
+void clear_self_refresh(struct mrc_params *mrc_params)
+{
+	ENTERFN();
+
+	/* clear the PMSTS Channel Self Refresh bits */
+	mrc_write_mask(MEM_CTLR, PMSTS, BIT0, BIT0);
+
+	LEAVEFN();
+}
+
+/* It will initialize timing registers in the MCU (DTR0..DTR4) */
+void prog_ddr_timing_control(struct mrc_params *mrc_params)
+{
+	uint8_t tcl, wl;
+	uint8_t trp, trcd, tras, twr, twtr, trrd, trtp, tfaw;
+	uint32_t tck;
+	u32 dtr0, dtr1, dtr2, dtr3, dtr4;
+	u32 tmp1, tmp2;
+
+	ENTERFN();
+
+	/* mcu_init starts */
+	mrc_post_code(0x02, 0x00);
+
+	dtr0 = msg_port_read(MEM_CTLR, DTR0);
+	dtr1 = msg_port_read(MEM_CTLR, DTR1);
+	dtr2 = msg_port_read(MEM_CTLR, DTR2);
+	dtr3 = msg_port_read(MEM_CTLR, DTR3);
+	dtr4 = msg_port_read(MEM_CTLR, DTR4);
+
+	tck = t_ck[mrc_params->ddr_speed];	/* Clock in picoseconds */
+	tcl = mrc_params->params.cl;		/* CAS latency in clocks */
+	trp = tcl;	/* Per CAT MRC */
+	trcd = tcl;	/* Per CAT MRC */
+	tras = MCEIL(mrc_params->params.ras, tck);
+
+	/* Per JEDEC: tWR=15000ps DDR2/3 from 800-1600 */
+	twr = MCEIL(15000, tck);
+
+	twtr = MCEIL(mrc_params->params.wtr, tck);
+	trrd = MCEIL(mrc_params->params.rrd, tck);
+	trtp = 4;	/* Valid for 800 and 1066, use 5 for 1333 */
+	tfaw = MCEIL(mrc_params->params.faw, tck);
+
+	wl = 5 + mrc_params->ddr_speed;
+
+	dtr0 &= ~(BIT0 | BIT1);
+	dtr0 |= mrc_params->ddr_speed;
+	dtr0 &= ~(BIT12 | BIT13 | BIT14);
+	tmp1 = tcl - 5;
+	dtr0 |= ((tcl - 5) << 12);
+	dtr0 &= ~(BIT4 | BIT5 | BIT6 | BIT7);
+	dtr0 |= ((trp - 5) << 4);	/* 5 bit DRAM Clock */
+	dtr0 &= ~(BIT8 | BIT9 | BIT10 | BIT11);
+	dtr0 |= ((trcd - 5) << 8);	/* 5 bit DRAM Clock */
+
+	dtr1 &= ~(BIT0 | BIT1 | BIT2);
+	tmp2 = wl - 3;
+	dtr1 |= (wl - 3);
+	dtr1 &= ~(BIT8 | BIT9 | BIT10 | BIT11);
+	dtr1 |= ((wl + 4 + twr - 14) << 8);	/* Change to tWTP */
+	dtr1 &= ~(BIT28 | BIT29 | BIT30);
+	dtr1 |= ((MMAX(trtp, 4) - 3) << 28);	/* 4 bit DRAM Clock */
+	dtr1 &= ~(BIT24 | BIT25);
+	dtr1 |= ((trrd - 4) << 24);		/* 4 bit DRAM Clock */
+	dtr1 &= ~(BIT4 | BIT5);
+	dtr1 |= (1 << 4);
+	dtr1 &= ~(BIT20 | BIT21 | BIT22 | BIT23);
+	dtr1 |= ((tras - 14) << 20);		/* 6 bit DRAM Clock */
+	dtr1 &= ~(BIT16 | BIT17 | BIT18 | BIT19);
+	dtr1 |= ((((tfaw + 1) >> 1) - 5) << 16);/* 4 bit DRAM Clock */
+	/* Set 4 Clock CAS to CAS delay (multi-burst) */
+	dtr1 &= ~(BIT12 | BIT13);
+
+	dtr2 &= ~(BIT0 | BIT1 | BIT2);
+	dtr2 |= 1;
+	dtr2 &= ~(BIT8 | BIT9 | BIT10);
+	dtr2 |= (2 << 8);
+	dtr2 &= ~(BIT16 | BIT17 | BIT18 | BIT19);
+	dtr2 |= (2 << 16);
+
+	dtr3 &= ~(BIT0 | BIT1 | BIT2);
+	dtr3 |= 2;
+	dtr3 &= ~(BIT4 | BIT5 | BIT6);
+	dtr3 |= (2 << 4);
+
+	dtr3 &= ~(BIT8 | BIT9 | BIT10 | BIT11);
+	if (mrc_params->ddr_speed == DDRFREQ_800) {
+		/* Extended RW delay (+1) */
+		dtr3 |= ((tcl - 5 + 1) << 8);
+	} else if (mrc_params->ddr_speed == DDRFREQ_1066) {
+		/* Extended RW delay (+1) */
+		dtr3 |= ((tcl - 5 + 1) << 8);
+	}
+
+	dtr3 &= ~(BIT13 | BIT14 | BIT15 | BIT16);
+	dtr3 |= ((4 + wl + twtr - 11) << 13);
+
+	dtr3 &= ~(BIT22 | BIT23);
+	if (mrc_params->ddr_speed == DDRFREQ_800)
+		dtr3 |= ((MMAX(0, 1 - 1)) << 22);
+	else
+		dtr3 |= ((MMAX(0, 2 - 1)) << 22);
+
+	dtr4 &= ~(BIT0 | BIT1);
+	dtr4 |= 1;
+	dtr4 &= ~(BIT4 | BIT5 | BIT6);
+	dtr4 |= (1 << 4);
+	dtr4 &= ~(BIT8 | BIT9 | BIT10);
+	dtr4 |= ((1 + tmp1 - tmp2 + 2) << 8);
+	dtr4 &= ~(BIT12 | BIT13 | BIT14);
+	dtr4 |= ((1 + tmp1 - tmp2 + 2) << 12);
+	dtr4 &= ~(BIT15 | BIT16);
+
+	msg_port_write(MEM_CTLR, DTR0, dtr0);
+	msg_port_write(MEM_CTLR, DTR1, dtr1);
+	msg_port_write(MEM_CTLR, DTR2, dtr2);
+	msg_port_write(MEM_CTLR, DTR3, dtr3);
+	msg_port_write(MEM_CTLR, DTR4, dtr4);
+
+	LEAVEFN();
+}
+
+/* Configure MCU before jedec init sequence */
+void prog_decode_before_jedec(struct mrc_params *mrc_params)
+{
+	u32 drp;
+	u32 drfc;
+	u32 dcal;
+	u32 dsch;
+	u32 dpmc0;
+
+	ENTERFN();
+
+	/* Disable power saving features */
+	dpmc0 = msg_port_read(MEM_CTLR, DPMC0);
+	dpmc0 |= (BIT24 | BIT25);
+	dpmc0 &= ~(BIT16 | BIT17 | BIT18);
+	dpmc0 &= ~BIT23;
+	msg_port_write(MEM_CTLR, DPMC0, dpmc0);
+
+	/* Disable out of order transactions */
+	dsch = msg_port_read(MEM_CTLR, DSCH);
+	dsch |= (BIT8 | BIT12);
+	msg_port_write(MEM_CTLR, DSCH, dsch);
+
+	/* Disable issuing the REF command */
+	drfc = msg_port_read(MEM_CTLR, DRFC);
+	drfc &= ~(BIT12 | BIT13 | BIT14);
+	msg_port_write(MEM_CTLR, DRFC, drfc);
+
+	/* Disable ZQ calibration short */
+	dcal = msg_port_read(MEM_CTLR, DCAL);
+	dcal &= ~(BIT8 | BIT9 | BIT10);
+	dcal &= ~(BIT12 | BIT13);
+	msg_port_write(MEM_CTLR, DCAL, dcal);
+
+	/*
+	 * Training performed in address mode 0, rank population has limited
+	 * impact, however simulator complains if enabled non-existing rank.
+	 */
+	drp = 0;
+	if (mrc_params->rank_enables & 1)
+		drp |= BIT0;
+	if (mrc_params->rank_enables & 2)
+		drp |= BIT1;
+	msg_port_write(MEM_CTLR, DRP, drp);
+
+	LEAVEFN();
+}
+
+/*
+ * After Cold Reset, BIOS should set COLDWAKE bit to 1 before
+ * sending the WAKE message to the Dunit.
+ *
+ * For Standby Exit, or any other mode in which the DRAM is in
+ * SR, this bit must be set to 0.
+ */
+void perform_ddr_reset(struct mrc_params *mrc_params)
+{
+	ENTERFN();
+
+	/* Set COLDWAKE bit before sending the WAKE message */
+	mrc_write_mask(MEM_CTLR, DRMC, BIT16, BIT16);
+
+	/* Send wake command to DUNIT (MUST be done before JEDEC) */
+	dram_wake_command();
+
+	/* Set default value */
+	msg_port_write(MEM_CTLR, DRMC,
+		       (mrc_params->rd_odt_value == 0 ? BIT12 : 0));
+
+	LEAVEFN();
+}
+
+
+/*
+ * This function performs some initialization on the DDRIO unit.
+ * This function is dependent on BOARD_ID, DDR_SPEED, and CHANNEL_ENABLES.
+ */
+void ddrphy_init(struct mrc_params *mrc_params)
+{
+	uint32_t temp;
+	uint8_t ch;	/* channel counter */
+	uint8_t rk;	/* rank counter */
+	uint8_t bl_grp;	/*  byte lane group counter (2 BLs per module) */
+	uint8_t bl_divisor = 1;	/* byte lane divisor */
+	/* For DDR3 --> 0 == 800, 1 == 1066, 2 == 1333 */
+	uint8_t speed = mrc_params->ddr_speed & (BIT1 | BIT0);
+	uint8_t cas;
+	uint8_t cwl;
+
+	ENTERFN();
+
+	cas = mrc_params->params.cl;
+	cwl = 5 + mrc_params->ddr_speed;
+
+	/* ddrphy_init starts */
+	mrc_post_code(0x03, 0x00);
+
+	/*
+	 * HSD#231531
+	 * Make sure IOBUFACT is deasserted before initializing the DDR PHY
+	 *
+	 * HSD#234845
+	 * Make sure WRPTRENABLE is deasserted before initializing the DDR PHY
+	 */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* Deassert DDRPHY Initialization Complete */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMCONFIG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				~BIT20, BIT20);	/* SPID_INIT_COMPLETE=0 */
+			/* Deassert IOBUFACT */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCFGREG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				~BIT2, BIT2);	/* IOBUFACTRST_N=0 */
+			/* Disable WRPTR */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPTRREG + (ch * DDRIOCCC_CH_OFFSET)),
+				~BIT0, BIT0);	/* WRPTRENABLE=0 */
+		}
+	}
+
+	/* Put PHY in reset */
+	mrc_alt_write_mask(DDRPHY, MASTERRSTN, 0, BIT0);
+
+	/* Initialize DQ01, DQ23, CMD, CLK-CTL, COMP modules */
+
+	/* STEP0 */
+	mrc_post_code(0x03, 0x10);
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* DQ01-DQ23 */
+			for (bl_grp = 0;
+			     bl_grp < ((NUM_BYTE_LANES / bl_divisor) / 2);
+			     bl_grp++) {
+				/* Analog MUX select - IO2xCLKSEL */
+				mrc_alt_write_mask(DDRPHY,
+					(DQOBSCKEBBCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					((bl_grp) ? (0x00) : (BIT22)), (BIT22));
+
+				/* ODT Strength */
+				switch (mrc_params->rd_odt_value) {
+				case 1:
+					temp = 0x3;
+					break;	/* 60 ohm */
+				case 2:
+					temp = 0x3;
+					break;	/* 120 ohm */
+				case 3:
+					temp = 0x3;
+					break;	/* 180 ohm */
+				default:
+					temp = 0x3;
+					break;	/* 120 ohm */
+				}
+
+				/* ODT strength */
+				mrc_alt_write_mask(DDRPHY,
+					(B0RXIOBUFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(temp << 5), (BIT6 | BIT5));
+				/* ODT strength */
+				mrc_alt_write_mask(DDRPHY,
+					(B1RXIOBUFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(temp << 5), (BIT6 | BIT5));
+
+				/* Dynamic ODT/DIFFAMP */
+				temp = (((cas) << 24) | ((cas) << 16) |
+					((cas) << 8) | ((cas) << 0));
+				switch (speed) {
+				case 0:
+					temp -= 0x01010101;
+					break;	/* 800 */
+				case 1:
+					temp -= 0x02020202;
+					break;	/* 1066 */
+				case 2:
+					temp -= 0x03030303;
+					break;	/* 1333 */
+				case 3:
+					temp -= 0x04040404;
+					break;	/* 1600 */
+				}
+
+				/* Launch Time: ODT, DIFFAMP, ODT, DIFFAMP */
+				mrc_alt_write_mask(DDRPHY,
+					(B01LATCTL1 +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					temp,
+					(BIT28 | BIT27 | BIT26 | BIT25 | BIT24 |
+					BIT20 | BIT19 | BIT18 | BIT17 | BIT16 |
+					BIT12 | BIT11 | BIT10 | BIT9 | BIT8 |
+					BIT4 | BIT3 | BIT2 | BIT1 | BIT0));
+				switch (speed) {
+				/* HSD#234715 */
+				case 0:
+					temp = ((0x06 << 16) | (0x07 << 8));
+					break;	/* 800 */
+				case 1:
+					temp = ((0x07 << 16) | (0x08 << 8));
+					break;	/* 1066 */
+				case 2:
+					temp = ((0x09 << 16) | (0x0A << 8));
+					break;	/* 1333 */
+				case 3:
+					temp = ((0x0A << 16) | (0x0B << 8));
+					break;	/* 1600 */
+				}
+
+				/* On Duration: ODT, DIFFAMP */
+				mrc_alt_write_mask(DDRPHY,
+					(B0ONDURCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					temp,
+					(BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+					BIT16 | BIT13 | BIT12 | BIT11 | BIT10 |
+					BIT9 | BIT8));
+				/* On Duration: ODT, DIFFAMP */
+				mrc_alt_write_mask(DDRPHY,
+					(B1ONDURCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					temp,
+					(BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+					BIT16 | BIT13 | BIT12 | BIT11 | BIT10 |
+					BIT9 | BIT8));
+
+				switch (mrc_params->rd_odt_value) {
+				case 0:
+					/* override DIFFAMP=on, ODT=off */
+					temp = ((0x3F << 16) | (0x3f << 10));
+					break;
+				default:
+					/* override DIFFAMP=on, ODT=on */
+					temp = ((0x3F << 16) | (0x2A << 10));
+					break;
+				}
+
+				/* Override: DIFFAMP, ODT */
+				mrc_alt_write_mask(DDRPHY,
+					(B0OVRCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					temp,
+					(BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+					BIT16 | BIT15 | BIT14 | BIT13 | BIT12 |
+					BIT11 | BIT10));
+				/* Override: DIFFAMP, ODT */
+				mrc_alt_write_mask(DDRPHY,
+					(B1OVRCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					temp,
+					(BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+					BIT16 | BIT15 | BIT14 | BIT13 | BIT12 |
+					BIT11 | BIT10));
+
+				/* DLL Setup */
+
+				/* 1xCLK Domain Timings: tEDP,RCVEN,WDQS (PO) */
+				mrc_alt_write_mask(DDRPHY,
+					(B0LATCTL0 +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(((cas + 7) << 16) | ((cas - 4) << 8) |
+					((cwl - 2) << 0)),
+					(BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+					BIT16 | BIT12 | BIT11 | BIT10 | BIT9 |
+					BIT8 | BIT4 | BIT3 | BIT2 | BIT1 |
+					BIT0));
+				mrc_alt_write_mask(DDRPHY,
+					(B1LATCTL0 +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(((cas + 7) << 16) | ((cas - 4) << 8) |
+					((cwl - 2) << 0)),
+					(BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+					BIT16 | BIT12 | BIT11 | BIT10 | BIT9 |
+					BIT8 | BIT4 | BIT3 | BIT2 | BIT1 |
+					BIT0));
+
+				/* RCVEN Bypass (PO) */
+				mrc_alt_write_mask(DDRPHY,
+					(B0RXIOBUFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					((0x0 << 7) | (0x0 << 0)),
+					(BIT7 | BIT0));
+				mrc_alt_write_mask(DDRPHY,
+					(B1RXIOBUFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					((0x0 << 7) | (0x0 << 0)),
+					(BIT7 | BIT0));
+
+				/* TX */
+				mrc_alt_write_mask(DDRPHY,
+					(DQCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(BIT16), (BIT16));
+				mrc_alt_write_mask(DDRPHY,
+					(B01PTRCTL1 +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(BIT8), (BIT8));
+
+				/* RX (PO) */
+				/* Internal Vref Code, Enable#, Ext_or_Int (1=Ext) */
+				mrc_alt_write_mask(DDRPHY,
+					(B0VREFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					((0x03 << 2) | (0x0 << 1) | (0x0 << 0)),
+					(BIT7 | BIT6 | BIT5 | BIT4 | BIT3 |
+					BIT2 | BIT1 | BIT0));
+				/* Internal Vref Code, Enable#, Ext_or_Int (1=Ext) */
+				mrc_alt_write_mask(DDRPHY,
+					(B1VREFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					((0x03 << 2) | (0x0 << 1) | (0x0 << 0)),
+					(BIT7 | BIT6 | BIT5 | BIT4 | BIT3 |
+					BIT2 | BIT1 | BIT0));
+				/* Per-Bit De-Skew Enable */
+				mrc_alt_write_mask(DDRPHY,
+					(B0RXIOBUFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(0), (BIT4));
+				/* Per-Bit De-Skew Enable */
+				mrc_alt_write_mask(DDRPHY,
+					(B1RXIOBUFCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(0), (BIT4));
+			}
+
+			/* CLKEBB */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDOBSCKEBBCTL + (ch * DDRIOCCC_CH_OFFSET)),
+				0, (BIT23));
+
+			/* Enable tristate control of cmd/address bus */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCFGREG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				0, (BIT1 | BIT0));
+
+			/* ODT RCOMP */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDRCOMPODT + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x03 << 5) | (0x03 << 0)),
+				(BIT9 | BIT8 | BIT7 | BIT6 | BIT5 | BIT4 |
+				BIT3 | BIT2 | BIT1 | BIT0));
+
+			/* CMDPM* registers must be programmed in this order */
+
+			/* Turn On Delays: SFR (regulator), MPLL */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMDLYREG4 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0xFFFFU << 16) | (0xFFFF << 0)),
+				0xFFFFFFFF);
+			/*
+			 * Delays: ASSERT_IOBUFACT_to_ALLON0_for_PM_MSG_3,
+			 * VREG (MDLL) Turn On, ALLON0_to_DEASSERT_IOBUFACT
+			 * for_PM_MSG_gt0, MDLL Turn On
+			 */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMDLYREG3 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0xFU << 28) | (0xFFF << 16) | (0xF << 12) |
+				(0x616 << 0)), 0xFFFFFFFF);
+			/* MPLL Divider Reset Delays */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMDLYREG2 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0xFFU << 24) | (0xFF << 16) | (0xFF << 8) |
+				(0xFF << 0)), 0xFFFFFFFF);
+			/* Turn Off Delays: VREG, Staggered MDLL, MDLL, PI */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMDLYREG1 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0xFFU << 24) | (0xFF << 16) | (0xFF << 8) |
+				(0xFF << 0)), 0xFFFFFFFF);
+			/* Turn On Delays: MPLL, Staggered MDLL, PI, IOBUFACT */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMDLYREG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0xFFU << 24) | (0xFF << 16) | (0xFF << 8) |
+				(0xFF << 0)), 0xFFFFFFFF);
+			/* Allow PUnit signals */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMCONFIG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x6 << 8) | BIT6 | (0x4 << 0)),
+				(BIT31 | BIT30 | BIT29 | BIT28 | BIT27 | BIT26 |
+				BIT25 | BIT24 | BIT23 | BIT22 | BIT21 | BIT11 |
+				BIT10 | BIT9 | BIT8 | BIT6 | BIT3 | BIT2 |
+				BIT1 | BIT0));
+			/* DLL_VREG Bias Trim, VREF Tuning for DLL_VREG */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDMDLLCTL + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x3 << 4) | (0x7 << 0)),
+				(BIT6 | BIT5 | BIT4 | BIT3 | BIT2 | BIT1 |
+				BIT0));
+
+			/* CLK-CTL */
+			mrc_alt_write_mask(DDRPHY,
+				(CCOBSCKEBBCTL + (ch * DDRIOCCC_CH_OFFSET)),
+				0, BIT24);	/* CLKEBB */
+			/* Buffer Enable: CS,CKE,ODT,CLK */
+			mrc_alt_write_mask(DDRPHY,
+				(CCCFGREG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x0 << 16) | (0x0 << 12) | (0x0 << 8) |
+				(0xF << 4) | BIT0),
+				(BIT19 | BIT18 | BIT17 | BIT16 | BIT15 | BIT14 |
+				BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8 |
+				BIT7 | BIT6 | BIT5 | BIT4 | BIT0));
+			/* ODT RCOMP */
+			mrc_alt_write_mask(DDRPHY,
+				(CCRCOMPODT + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x03 << 8) | (0x03 << 0)),
+				(BIT12 | BIT11 | BIT10 | BIT9 | BIT8 | BIT4 |
+				BIT3 | BIT2 | BIT1 | BIT0));
+			/* DLL_VREG Bias Trim, VREF Tuning for DLL_VREG */
+			mrc_alt_write_mask(DDRPHY,
+				(CCMDLLCTL + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x3 << 4) | (0x7 << 0)),
+				(BIT6 | BIT5 | BIT4 | BIT3 | BIT2 | BIT1 |
+				BIT0));
+
+			/*
+			 * COMP (RON channel specific)
+			 * - DQ/DQS/DM RON: 32 Ohm
+			 * - CTRL/CMD RON: 27 Ohm
+			 * - CLK RON: 26 Ohm
+			 */
+			/* RCOMP Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQVREFCH0 +  (ch * DDRCOMP_CH_OFFSET)),
+				((0x08 << 24) | (0x03 << 16)),
+				(BIT29 | BIT28 | BIT27 | BIT26 | BIT25 |
+				BIT24 | BIT21 | BIT20 | BIT19 | BIT18 |
+				BIT17 | BIT16));
+			/* RCOMP Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x0C << 24) | (0x03 << 16)),
+				(BIT29 | BIT28 | BIT27 | BIT26 | BIT25 |
+				BIT24 | BIT21 | BIT20 | BIT19 | BIT18 |
+				BIT17 | BIT16));
+			/* RCOMP Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x0F << 24) | (0x03 << 16)),
+				(BIT29 | BIT28 | BIT27 | BIT26 | BIT25 |
+				BIT24 | BIT21 | BIT20 | BIT19 | BIT18 |
+				BIT17 | BIT16));
+			/* RCOMP Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x08 << 24) | (0x03 << 16)),
+				(BIT29 | BIT28 | BIT27 | BIT26 | BIT25 |
+				BIT24 | BIT21 | BIT20 | BIT19 | BIT18 |
+				BIT17 | BIT16));
+			/* RCOMP Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CTLVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x0C << 24) | (0x03 << 16)),
+				(BIT29 | BIT28 | BIT27 | BIT26 | BIT25 |
+				BIT24 | BIT21 | BIT20 | BIT19 | BIT18 |
+				BIT17 | BIT16));
+
+			/* DQS Swapped Input Enable */
+			mrc_alt_write_mask(DDRPHY,
+				(COMPEN1CH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT19 | BIT17),
+				(BIT31 | BIT30 | BIT19 | BIT17 |
+				BIT15 | BIT14));
+
+			/* ODT VREF = 1.5 x 274/360+274 = 0.65V (code of ~50) */
+			/* ODT Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x32 << 8) | (0x03 << 0)),
+				(BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8 |
+				BIT5 | BIT4 | BIT3 | BIT2 | BIT1 | BIT0));
+			/* ODT Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x32 << 8) | (0x03 << 0)),
+				(BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8 |
+				BIT5 | BIT4 | BIT3 | BIT2 | BIT1 | BIT0));
+			/* ODT Vref PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x0E << 8) | (0x05 << 0)),
+				(BIT13 | BIT12 | BIT11 | BIT10 | BIT9 | BIT8 |
+				BIT5 | BIT4 | BIT3 | BIT2 | BIT1 | BIT0));
+
+			/*
+			 * Slew rate settings are frequency specific,
+			 * numbers below are for 800Mhz (speed == 0)
+			 * - DQ/DQS/DM/CLK SR: 4V/ns,
+			 * - CTRL/CMD SR: 1.5V/ns
+			 */
+			temp = (0x0E << 16) | (0x0E << 12) | (0x08 << 8) |
+				(0x0B << 4) | (0x0B << 0);
+			/* DCOMP Delay Select: CTL,CMD,CLK,DQS,DQ */
+			mrc_alt_write_mask(DDRPHY,
+				(DLYSELCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				temp,
+				(BIT19 | BIT18 | BIT17 | BIT16 | BIT15 |
+				BIT14 | BIT13 | BIT12 | BIT11 | BIT10 |
+				BIT9 | BIT8 | BIT7 | BIT6 | BIT5 | BIT4 |
+				BIT3 | BIT2 | BIT1 | BIT0));
+			/* TCO Vref CLK,DQS,DQ */
+			mrc_alt_write_mask(DDRPHY,
+				(TCOVREFCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x05 << 16) | (0x05 << 8) | (0x05 << 0)),
+				(BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+				BIT16 | BIT13 | BIT12 | BIT11 | BIT10 |
+				BIT9 | BIT8 | BIT5 | BIT4 | BIT3 | BIT2 |
+				BIT1 | BIT0));
+			/* ODTCOMP CMD/CTL PU/PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CCBUFODTCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				((0x03 << 8) | (0x03 << 0)),
+				(BIT12 | BIT11 | BIT10 | BIT9 | BIT8 |
+				BIT4 | BIT3 | BIT2 | BIT1 | BIT0));
+			/* COMP */
+			mrc_alt_write_mask(DDRPHY,
+				(COMPEN0CH0 + (ch * DDRCOMP_CH_OFFSET)),
+				0, (BIT31 | BIT30 | BIT8));
+
+#ifdef BACKUP_COMPS
+			/* DQ COMP Overrides */
+			/* RCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQDRVPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* RCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQDRVPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQDLYPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x10 << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQDLYPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x10 << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* ODTCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQODTPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* ODTCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQODTPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* TCOCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQTCOPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31), (BIT31));
+			/* TCOCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQTCOPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31), (BIT31));
+
+			/* DQS COMP Overrides */
+			/* RCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSDRVPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* RCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSDRVPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSDLYPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x10 << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSDLYPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x10 << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* ODTCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSODTPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* ODTCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSODTPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* TCOCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSTCOPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31), (BIT31));
+			/* TCOCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSTCOPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31), (BIT31));
+
+			/* CLK COMP Overrides */
+			/* RCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKDRVPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0C << 16)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* RCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKDRVPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0C << 16)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKDLYPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x07 << 16)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKDLYPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x07 << 16)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* ODTCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKODTPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* ODTCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKODTPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | (0x0B << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* TCOCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKTCOPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31), (BIT31));
+			/* TCOCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKTCOPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31), (BIT31));
+
+			/* CMD COMP Overrides */
+			/* RCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDDRVPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0D << 16)),
+				(BIT31 | BIT21 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* RCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDDRVPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0D << 16)),
+				(BIT31 | BIT21 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDDLYPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDDLYPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+
+			/* CTL COMP Overrides */
+			/* RCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CTLDRVPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0D << 16)),
+				(BIT31 | BIT21 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* RCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CTLDRVPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0D << 16)),
+				(BIT31 | BIT21 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CTLDLYPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* DCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CTLDLYPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x0A << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+#else
+			/* DQ TCOCOMP Overrides */
+			/* TCOCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQTCOPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x1F << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* TCOCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQTCOPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x1F << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+
+			/* DQS TCOCOMP Overrides */
+			/* TCOCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSTCOPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x1F << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* TCOCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(DQSTCOPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x1F << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+
+			/* CLK TCOCOMP Overrides */
+			/* TCOCOMP PU */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKTCOPUCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x1F << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+			/* TCOCOMP PD */
+			mrc_alt_write_mask(DDRPHY,
+				(CLKTCOPDCTLCH0 + (ch * DDRCOMP_CH_OFFSET)),
+				(BIT31 | (0x1F << 16)),
+				(BIT31 | BIT20 | BIT19 |
+				BIT18 | BIT17 | BIT16));
+#endif
+
+			/* program STATIC delays */
+#ifdef BACKUP_WCMD
+			set_wcmd(ch, ddr_wcmd[PLATFORM_ID]);
+#else
+			set_wcmd(ch, ddr_wclk[PLATFORM_ID] + HALF_CLK);
+#endif
+
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1<<rk)) {
+					set_wclk(ch, rk, ddr_wclk[PLATFORM_ID]);
+#ifdef BACKUP_WCTL
+					set_wctl(ch, rk, ddr_wctl[PLATFORM_ID]);
+#else
+					set_wctl(ch, rk, ddr_wclk[PLATFORM_ID] + HALF_CLK);
+#endif
+				}
+			}
+		}
+	}
+
+	/* COMP (non channel specific) */
+	/* RCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANADRVPUCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANADRVPDCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CMDANADRVPUCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CMDANADRVPDCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANADRVPUCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANADRVPDCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANADRVPUCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANADRVPDCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CTLANADRVPUCTL), (BIT30), (BIT30));
+	/* RCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CTLANADRVPDCTL), (BIT30), (BIT30));
+	/* ODT: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANAODTPUCTL), (BIT30), (BIT30));
+	/* ODT: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANAODTPDCTL), (BIT30), (BIT30));
+	/* ODT: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANAODTPUCTL), (BIT30), (BIT30));
+	/* ODT: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANAODTPDCTL), (BIT30), (BIT30));
+	/* ODT: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANAODTPUCTL), (BIT30), (BIT30));
+	/* ODT: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANAODTPDCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANADLYPUCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANADLYPDCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CMDANADLYPUCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CMDANADLYPDCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANADLYPUCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANADLYPDCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANADLYPUCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANADLYPDCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CTLANADLYPUCTL), (BIT30), (BIT30));
+	/* DCOMP: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CTLANADLYPDCTL), (BIT30), (BIT30));
+	/* TCO: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANATCOPUCTL), (BIT30), (BIT30));
+	/* TCO: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQANATCOPDCTL), (BIT30), (BIT30));
+	/* TCO: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANATCOPUCTL), (BIT30), (BIT30));
+	/* TCO: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (CLKANATCOPDCTL), (BIT30), (BIT30));
+	/* TCO: Dither PU Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANATCOPUCTL), (BIT30), (BIT30));
+	/* TCO: Dither PD Enable */
+	mrc_alt_write_mask(DDRPHY, (DQSANATCOPDCTL), (BIT30), (BIT30));
+	/* TCOCOMP: Pulse Count */
+	mrc_alt_write_mask(DDRPHY, (TCOCNTCTRL), (0x1 << 0), (BIT1 | BIT0));
+	/* ODT: CMD/CTL PD/PU */
+	mrc_alt_write_mask(DDRPHY,
+		(CHNLBUFSTATIC), ((0x03 << 24) | (0x03 << 16)),
+		(BIT28 | BIT27 | BIT26 | BIT25 | BIT24 |
+		BIT20 | BIT19 | BIT18 | BIT17 | BIT16));
+	/* Set 1us counter */
+	mrc_alt_write_mask(DDRPHY,
+		(MSCNTR), (0x64 << 0),
+		(BIT7 | BIT6 | BIT5 | BIT4 | BIT3 | BIT2 | BIT1 | BIT0));
+	mrc_alt_write_mask(DDRPHY,
+		(LATCH1CTL), (0x1 << 28),
+		(BIT30 | BIT29 | BIT28));
+
+	/* Release PHY from reset */
+	mrc_alt_write_mask(DDRPHY, MASTERRSTN, BIT0, BIT0);
+
+	/* STEP1 */
+	mrc_post_code(0x03, 0x11);
+
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* DQ01-DQ23 */
+			for (bl_grp = 0;
+			     bl_grp < ((NUM_BYTE_LANES / bl_divisor) / 2);
+			     bl_grp++) {
+				mrc_alt_write_mask(DDRPHY,
+					(DQMDLLCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(BIT13),
+					(BIT13));	/* Enable VREG */
+				delay_n(3);
+			}
+
+			/* ECC */
+			mrc_alt_write_mask(DDRPHY, (ECCMDLLCTL),
+				(BIT13), (BIT13));	/* Enable VREG */
+			delay_n(3);
+			/* CMD */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDMDLLCTL + (ch * DDRIOCCC_CH_OFFSET)),
+				(BIT13), (BIT13));	/* Enable VREG */
+			delay_n(3);
+			/* CLK-CTL */
+			mrc_alt_write_mask(DDRPHY,
+				(CCMDLLCTL + (ch * DDRIOCCC_CH_OFFSET)),
+				(BIT13), (BIT13));	/* Enable VREG */
+			delay_n(3);
+		}
+	}
+
+	/* STEP2 */
+	mrc_post_code(0x03, 0x12);
+	delay_n(200);
+
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* DQ01-DQ23 */
+			for (bl_grp = 0;
+			     bl_grp < ((NUM_BYTE_LANES / bl_divisor) / 2);
+			     bl_grp++) {
+				mrc_alt_write_mask(DDRPHY,
+					(DQMDLLCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(BIT17),
+					(BIT17));	/* Enable MCDLL */
+				delay_n(50);
+			}
+
+		/* ECC */
+		mrc_alt_write_mask(DDRPHY, (ECCMDLLCTL),
+			(BIT17), (BIT17));	/* Enable MCDLL */
+		delay_n(50);
+		/* CMD */
+		mrc_alt_write_mask(DDRPHY,
+			(CMDMDLLCTL + (ch * DDRIOCCC_CH_OFFSET)),
+			(BIT18), (BIT18));	/* Enable MCDLL */
+		delay_n(50);
+		/* CLK-CTL */
+		mrc_alt_write_mask(DDRPHY,
+			(CCMDLLCTL + (ch * DDRIOCCC_CH_OFFSET)),
+			(BIT18), (BIT18));	/* Enable MCDLL */
+		delay_n(50);
+		}
+	}
+
+	/* STEP3: */
+	mrc_post_code(0x03, 0x13);
+	delay_n(100);
+
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* DQ01-DQ23 */
+			for (bl_grp = 0;
+			     bl_grp < ((NUM_BYTE_LANES / bl_divisor) / 2);
+			     bl_grp++) {
+#ifdef FORCE_16BIT_DDRIO
+				temp = ((bl_grp) &&
+					(mrc_params->channel_width == X16)) ?
+					((0x1 << 12) | (0x1 << 8) |
+					(0xF << 4) | (0xF << 0)) :
+					((0xF << 12) | (0xF << 8) |
+					(0xF << 4) | (0xF << 0));
+#else
+				temp = ((0xF << 12) | (0xF << 8) |
+					(0xF << 4) | (0xF << 0));
+#endif
+				/* Enable TXDLL */
+				mrc_alt_write_mask(DDRPHY,
+					(DQDLLTXCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					temp, 0xFFFF);
+				delay_n(3);
+				/* Enable RXDLL */
+				mrc_alt_write_mask(DDRPHY,
+					(DQDLLRXCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(BIT3 | BIT2 | BIT1 | BIT0),
+					(BIT3 | BIT2 | BIT1 | BIT0));
+				delay_n(3);
+				/* Enable RXDLL Overrides BL0 */
+				mrc_alt_write_mask(DDRPHY,
+					(B0OVRCTL +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(BIT3 | BIT2 | BIT1 | BIT0),
+					(BIT3 | BIT2 | BIT1 | BIT0));
+			}
+
+			/* ECC */
+			temp = ((0xF << 12) | (0xF << 8) |
+				(0xF << 4) | (0xF << 0));
+			mrc_alt_write_mask(DDRPHY, (ECCDLLTXCTL),
+				temp, 0xFFFF);
+			delay_n(3);
+
+			/* CMD (PO) */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDDLLTXCTL + (ch * DDRIOCCC_CH_OFFSET)),
+				temp, 0xFFFF);
+			delay_n(3);
+		}
+	}
+
+	/* STEP4 */
+	mrc_post_code(0x03, 0x14);
+
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* Host To Memory Clock Alignment (HMC) for 800/1066 */
+			for (bl_grp = 0;
+			     bl_grp < ((NUM_BYTE_LANES / bl_divisor) / 2);
+			     bl_grp++) {
+				/* CLK_ALIGN_MOD_ID */
+				mrc_alt_write_mask(DDRPHY,
+					(DQCLKALIGNREG2 +
+					(bl_grp * DDRIODQ_BL_OFFSET) +
+					(ch * DDRIODQ_CH_OFFSET)),
+					(bl_grp) ? (0x3) : (0x1),
+					(BIT3 | BIT2 | BIT1 | BIT0));
+			}
+
+			mrc_alt_write_mask(DDRPHY,
+				(ECCCLKALIGNREG2 + (ch * DDRIODQ_CH_OFFSET)),
+				0x2,
+				(BIT3 | BIT2 | BIT1 | BIT0));
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCLKALIGNREG2 + (ch * DDRIODQ_CH_OFFSET)),
+				0x0,
+				(BIT3 | BIT2 | BIT1 | BIT0));
+			mrc_alt_write_mask(DDRPHY,
+				(CCCLKALIGNREG2 + (ch * DDRIODQ_CH_OFFSET)),
+				0x2,
+				(BIT3 | BIT2 | BIT1 | BIT0));
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCLKALIGNREG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				(0x2 << 4), (BIT5 | BIT4));
+			/*
+			 * NUM_SAMPLES, MAX_SAMPLES,
+			 * MACRO_PI_STEP, MICRO_PI_STEP
+			 */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCLKALIGNREG1 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x18 << 16) | (0x10 << 8) |
+				(0x8 << 2) | (0x1 << 0)),
+				(BIT22 | BIT21 | BIT20 | BIT19 | BIT18 | BIT17 |
+				BIT16 | BIT14 | BIT13 | BIT12 | BIT11 | BIT10 |
+				BIT9 | BIT8 | BIT7 | BIT6 | BIT5 | BIT4 | BIT3 |
+				BIT2 | BIT1 | BIT0));
+			/* TOTAL_NUM_MODULES, FIRST_U_PARTITION */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCLKALIGNREG2 + (ch * DDRIOCCC_CH_OFFSET)),
+				((0x10 << 16) | (0x4 << 8) | (0x2 << 4)),
+				(BIT20 | BIT19 | BIT18 | BIT17 | BIT16 |
+				BIT11 | BIT10 | BIT9 | BIT8 | BIT7 | BIT6 |
+				BIT5 | BIT4));
+#ifdef HMC_TEST
+			/* START_CLK_ALIGN=1 */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCLKALIGNREG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				BIT24, BIT24);
+			while (msg_port_alt_read(DDRPHY,
+				(CMDCLKALIGNREG0 + (ch * DDRIOCCC_CH_OFFSET))) &
+				BIT24)
+				;	/* wait for START_CLK_ALIGN=0 */
+#endif
+
+			/* Set RD/WR Pointer Seperation & COUNTEN & FIFOPTREN */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPTRREG + (ch * DDRIOCCC_CH_OFFSET)),
+				BIT0, BIT0);	/* WRPTRENABLE=1 */
+
+			/* COMP initial */
+			/* enable bypass for CLK buffer (PO) */
+			mrc_alt_write_mask(DDRPHY,
+				(COMPEN0CH0 + (ch * DDRCOMP_CH_OFFSET)),
+				BIT5, BIT5);
+			/* Initial COMP Enable */
+			mrc_alt_write_mask(DDRPHY, (CMPCTRL),
+				(BIT0), (BIT0));
+			/* wait for Initial COMP Enable = 0 */
+			while (msg_port_alt_read(DDRPHY, (CMPCTRL)) & BIT0)
+				;
+			/* disable bypass for CLK buffer (PO) */
+			mrc_alt_write_mask(DDRPHY,
+				(COMPEN0CH0 + (ch * DDRCOMP_CH_OFFSET)),
+				~BIT5, BIT5);
+
+			/* IOBUFACT */
+
+			/* STEP4a */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDCFGREG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				BIT2, BIT2);	/* IOBUFACTRST_N=1 */
+
+			/* DDRPHY initialization complete */
+			mrc_alt_write_mask(DDRPHY,
+				(CMDPMCONFIG0 + (ch * DDRIOCCC_CH_OFFSET)),
+				BIT20, BIT20);	/* SPID_INIT_COMPLETE=1 */
+		}
+	}
+
+	LEAVEFN();
+}
+
+/* This function performs JEDEC initialization on all enabled channels */
+void perform_jedec_init(struct mrc_params *mrc_params)
+{
+	uint8_t twr, wl, rank;
+	uint32_t tck;
+	u32 dtr0;
+	u32 drp;
+	u32 drmc;
+	u32 mrs0_cmd = 0;
+	u32 emrs1_cmd = 0;
+	u32 emrs2_cmd = 0;
+	u32 emrs3_cmd = 0;
+
+	ENTERFN();
+
+	/* jedec_init starts */
+	mrc_post_code(0x04, 0x00);
+
+	/* DDR3_RESET_SET=0, DDR3_RESET_RESET=1 */
+	mrc_alt_write_mask(DDRPHY, CCDDR3RESETCTL, BIT1, (BIT8 | BIT1));
+
+	/* Assert RESET# for 200us */
+	delay_u(200);
+
+	/* DDR3_RESET_SET=1, DDR3_RESET_RESET=0 */
+	mrc_alt_write_mask(DDRPHY, CCDDR3RESETCTL, BIT8, (BIT8 | BIT1));
+
+	dtr0 = msg_port_read(MEM_CTLR, DTR0);
+
+	/*
+	 * Set CKEVAL for populated ranks
+	 * then send NOP to each rank (#4550197)
+	 */
+
+	drp = msg_port_read(MEM_CTLR, DRP);
+	drp &= 0x3;
+
+	drmc = msg_port_read(MEM_CTLR, DRMC);
+	drmc &= 0xFFFFFFFC;
+	drmc |= (BIT4 | drp);
+
+	msg_port_write(MEM_CTLR, DRMC, drmc);
+
+	for (rank = 0; rank < NUM_RANKS; rank++) {
+		/* Skip to next populated rank */
+		if ((mrc_params->rank_enables & (1 << rank)) == 0)
+			continue;
+
+		dram_init_command(DCMD_NOP(rank));
+	}
+
+	msg_port_write(MEM_CTLR, DRMC,
+		(mrc_params->rd_odt_value == 0 ? BIT12 : 0));
+
+	/*
+	 * setup for emrs 2
+	 * BIT[15:11] --> Always "0"
+	 * BIT[10:09] --> Rtt_WR: want "Dynamic ODT Off" (0)
+	 * BIT[08]    --> Always "0"
+	 * BIT[07]    --> SRT: use sr_temp_range
+	 * BIT[06]    --> ASR: want "Manual SR Reference" (0)
+	 * BIT[05:03] --> CWL: use oem_tCWL
+	 * BIT[02:00] --> PASR: want "Full Array" (0)
+	 */
+	emrs2_cmd |= (2 << 3);
+	wl = 5 + mrc_params->ddr_speed;
+	emrs2_cmd |= ((wl - 5) << 9);
+	emrs2_cmd |= (mrc_params->sr_temp_range << 13);
+
+	/*
+	 * setup for emrs 3
+	 * BIT[15:03] --> Always "0"
+	 * BIT[02]    --> MPR: want "Normal Operation" (0)
+	 * BIT[01:00] --> MPR_Loc: want "Predefined Pattern" (0)
+	 */
+	emrs3_cmd |= (3 << 3);
+
+	/*
+	 * setup for emrs 1
+	 * BIT[15:13]     --> Always "0"
+	 * BIT[12:12]     --> Qoff: want "Output Buffer Enabled" (0)
+	 * BIT[11:11]     --> TDQS: want "Disabled" (0)
+	 * BIT[10:10]     --> Always "0"
+	 * BIT[09,06,02]  --> Rtt_nom: use rtt_nom_value
+	 * BIT[08]        --> Always "0"
+	 * BIT[07]        --> WR_LVL: want "Disabled" (0)
+	 * BIT[05,01]     --> DIC: use ron_value
+	 * BIT[04:03]     --> AL: additive latency want "0" (0)
+	 * BIT[00]        --> DLL: want "Enable" (0)
+	 *
+	 * (BIT5|BIT1) set Ron value
+	 * 00 --> RZQ/6 (40ohm)
+	 * 01 --> RZQ/7 (34ohm)
+	 * 1* --> RESERVED
+	 *
+	 * (BIT9|BIT6|BIT2) set Rtt_nom value
+	 * 000 --> Disabled
+	 * 001 --> RZQ/4 ( 60ohm)
+	 * 010 --> RZQ/2 (120ohm)
+	 * 011 --> RZQ/6 ( 40ohm)
+	 * 1** --> RESERVED
+	 */
+	emrs1_cmd |= (1 << 3);
+	emrs1_cmd &= ~BIT6;
+
+	if (mrc_params->ron_value == 0)
+		emrs1_cmd |= BIT7;
+	else
+		emrs1_cmd &= ~BIT7;
+
+	if (mrc_params->rtt_nom_value == 0)
+		emrs1_cmd |= (DDR3_EMRS1_RTTNOM_40 << 6);
+	else if (mrc_params->rtt_nom_value == 1)
+		emrs1_cmd |= (DDR3_EMRS1_RTTNOM_60 << 6);
+	else if (mrc_params->rtt_nom_value == 2)
+		emrs1_cmd |= (DDR3_EMRS1_RTTNOM_120 << 6);
+
+	/* save MRS1 value (excluding control fields) */
+	mrc_params->mrs1 = emrs1_cmd >> 6;
+
+	/*
+	 * setup for mrs 0
+	 * BIT[15:13]     --> Always "0"
+	 * BIT[12]        --> PPD: for Quark (1)
+	 * BIT[11:09]     --> WR: use oem_tWR
+	 * BIT[08]        --> DLL: want "Reset" (1, self clearing)
+	 * BIT[07]        --> MODE: want "Normal" (0)
+	 * BIT[06:04,02]  --> CL: use oem_tCAS
+	 * BIT[03]        --> RD_BURST_TYPE: want "Interleave" (1)
+	 * BIT[01:00]     --> BL: want "8 Fixed" (0)
+	 * WR:
+	 * 0 --> 16
+	 * 1 --> 5
+	 * 2 --> 6
+	 * 3 --> 7
+	 * 4 --> 8
+	 * 5 --> 10
+	 * 6 --> 12
+	 * 7 --> 14
+	 * CL:
+	 * BIT[02:02] "0" if oem_tCAS <= 11 (1866?)
+	 * BIT[06:04] use oem_tCAS-4
+	 */
+	mrs0_cmd |= BIT14;
+	mrs0_cmd |= BIT18;
+	mrs0_cmd |= ((((dtr0 >> 12) & 7) + 1) << 10);
+
+	tck = t_ck[mrc_params->ddr_speed];
+	/* Per JEDEC: tWR=15000ps DDR2/3 from 800-1600 */
+	twr = MCEIL(15000, tck);
+	mrs0_cmd |= ((twr - 4) << 15);
+
+	for (rank = 0; rank < NUM_RANKS; rank++) {
+		/* Skip to next populated rank */
+		if ((mrc_params->rank_enables & (1 << rank)) == 0)
+			continue;
+
+		emrs2_cmd |= (rank << 22);
+		dram_init_command(emrs2_cmd);
+
+		emrs3_cmd |= (rank << 22);
+		dram_init_command(emrs3_cmd);
+
+		emrs1_cmd |= (rank << 22);
+		dram_init_command(emrs1_cmd);
+
+		mrs0_cmd |= (rank << 22);
+		dram_init_command(mrs0_cmd);
+
+		dram_init_command(DCMD_ZQCL(rank));
+	}
+
+	LEAVEFN();
+}
+
+/*
+ * Dunit Initialization Complete
+ *
+ * Indicates that initialization of the Dunit has completed.
+ *
+ * Memory accesses are permitted and maintenance operation begins.
+ * Until this bit is set to a 1, the memory controller will not accept
+ * DRAM requests from the MEMORY_MANAGER or HTE.
+ */
+void set_ddr_init_complete(struct mrc_params *mrc_params)
+{
+	u32 dco;
+
+	ENTERFN();
+
+	dco = msg_port_read(MEM_CTLR, DCO);
+	dco &= ~BIT28;
+	dco |= BIT31;
+	msg_port_write(MEM_CTLR, DCO, dco);
+
+	LEAVEFN();
+}
+
+/*
+ * This function will retrieve relevant timing data
+ *
+ * This data will be used on subsequent boots to speed up boot times
+ * and is required for Suspend To RAM capabilities.
+ */
+void restore_timings(struct mrc_params *mrc_params)
+{
+	uint8_t ch, rk, bl;
+	const struct mrc_timings *mt = &mrc_params->timings;
+
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		for (rk = 0; rk < NUM_RANKS; rk++) {
+			for (bl = 0; bl < NUM_BYTE_LANES; bl++) {
+				set_rcvn(ch, rk, bl, mt->rcvn[ch][rk][bl]);
+				set_rdqs(ch, rk, bl, mt->rdqs[ch][rk][bl]);
+				set_wdqs(ch, rk, bl, mt->wdqs[ch][rk][bl]);
+				set_wdq(ch, rk, bl, mt->wdq[ch][rk][bl]);
+				if (rk == 0) {
+					/* VREF (RANK0 only) */
+					set_vref(ch, bl, mt->vref[ch][bl]);
+				}
+			}
+			set_wctl(ch, rk, mt->wctl[ch][rk]);
+		}
+		set_wcmd(ch, mt->wcmd[ch]);
+	}
+}
+
+/*
+ * Configure default settings normally set as part of read training
+ *
+ * Some defaults have to be set earlier as they may affect earlier
+ * training steps.
+ */
+void default_timings(struct mrc_params *mrc_params)
+{
+	uint8_t ch, rk, bl;
+
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		for (rk = 0; rk < NUM_RANKS; rk++) {
+			for (bl = 0; bl < NUM_BYTE_LANES; bl++) {
+				set_rdqs(ch, rk, bl, 24);
+				if (rk == 0) {
+					/* VREF (RANK0 only) */
+					set_vref(ch, bl, 32);
+				}
+			}
+		}
+	}
+}
+
+/*
+ * This function will perform our RCVEN Calibration Algorithm.
+ * We will only use the 2xCLK domain timings to perform RCVEN Calibration.
+ * All byte lanes will be calibrated "simultaneously" per channel per rank.
+ */
+void rcvn_cal(struct mrc_params *mrc_params)
+{
+	uint8_t ch;	/* channel counter */
+	uint8_t rk;	/* rank counter */
+	uint8_t bl;	/* byte lane counter */
+	uint8_t bl_divisor = (mrc_params->channel_width == X16) ? 2 : 1;
+
+#ifdef R2R_SHARING
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t final_delay[NUM_CHANNELS][NUM_BYTE_LANES];
+#ifndef BACKUP_RCVN
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t num_ranks_enabled = 0;
+#endif
+#endif
+
+#ifdef BACKUP_RCVN
+#else
+	uint32_t temp;
+	/* absolute PI value to be programmed on the byte lane */
+	uint32_t delay[NUM_BYTE_LANES];
+	u32 dtr1, dtr1_save;
+#endif
+
+	ENTERFN();
+
+	/* rcvn_cal starts */
+	mrc_post_code(0x05, 0x00);
+
+#ifndef BACKUP_RCVN
+	/* need separate burst to sample DQS preamble */
+	dtr1 = msg_port_read(MEM_CTLR, DTR1);
+	dtr1_save = dtr1;
+	dtr1 |= BIT12;
+	msg_port_write(MEM_CTLR, DTR1, dtr1);
+#endif
+
+#ifdef R2R_SHARING
+	/* need to set "final_delay[][]" elements to "0" */
+	memset((void *)(final_delay), 0x00, (size_t)sizeof(final_delay));
+#endif
+
+	/* loop through each enabled channel */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* perform RCVEN Calibration on a per rank basis */
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+					/*
+					 * POST_CODE here indicates the current
+					 * channel and rank being calibrated
+					 */
+					mrc_post_code(0x05, (0x10 + ((ch << 4) | rk)));
+
+#ifdef BACKUP_RCVN
+					/* et hard-coded timing values */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++)
+						set_rcvn(ch, rk, bl, ddr_rcvn[PLATFORM_ID]);
+#else
+					/* enable FIFORST */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl += 2) {
+						mrc_alt_write_mask(DDRPHY,
+							(B01PTRCTL1 +
+							((bl >> 1) * DDRIODQ_BL_OFFSET) +
+							(ch * DDRIODQ_CH_OFFSET)),
+							0, BIT8);
+					}
+					/* initialize the starting delay to 128 PI (cas +1 CLK) */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						/* 1x CLK domain timing is cas-4 */
+						delay[bl] = (4 + 1) * FULL_CLK;
+
+						set_rcvn(ch, rk, bl, delay[bl]);
+					}
+
+					/* now find the rising edge */
+					find_rising_edge(mrc_params, delay, ch, rk, true);
+
+					/* Now increase delay by 32 PI (1/4 CLK) to place in center of high pulse */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						delay[bl] += QRTR_CLK;
+						set_rcvn(ch, rk, bl, delay[bl]);
+					}
+					/* Now decrement delay by 128 PI (1 CLK) until we sample a "0" */
+					do {
+						temp = sample_dqs(mrc_params, ch, rk, true);
+						for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+							if (temp & (1 << bl)) {
+								if (delay[bl] >= FULL_CLK) {
+									delay[bl] -= FULL_CLK;
+									set_rcvn(ch, rk, bl, delay[bl]);
+								} else {
+									/* not enough delay */
+									training_message(ch, rk, bl);
+									mrc_post_code(0xEE, 0x50);
+								}
+							}
+						}
+					} while (temp & 0xFF);
+
+#ifdef R2R_SHARING
+					/* increment "num_ranks_enabled" */
+					num_ranks_enabled++;
+					/* Finally increment delay by 32 PI (1/4 CLK) to place in center of preamble */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						delay[bl] += QRTR_CLK;
+						/* add "delay[]" values to "final_delay[][]" for rolling average */
+						final_delay[ch][bl] += delay[bl];
+						/* set timing based on rolling average values */
+						set_rcvn(ch, rk, bl, ((final_delay[ch][bl]) / num_ranks_enabled));
+					}
+#else
+					/* Finally increment delay by 32 PI (1/4 CLK) to place in center of preamble */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						delay[bl] += QRTR_CLK;
+						set_rcvn(ch, rk, bl, delay[bl]);
+					}
+#endif
+
+					/* disable FIFORST */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl += 2) {
+						mrc_alt_write_mask(DDRPHY,
+							(B01PTRCTL1 +
+							((bl >> 1) * DDRIODQ_BL_OFFSET) +
+							(ch * DDRIODQ_CH_OFFSET)),
+							BIT8, BIT8);
+					}
+#endif
+				}
+			}
+		}
+	}
+
+#ifndef BACKUP_RCVN
+	/* restore original */
+	msg_port_write(MEM_CTLR, DTR1, dtr1_save);
+#endif
+
+	LEAVEFN();
+}
+
+/*
+ * This function will perform the Write Levelling algorithm
+ * (align WCLK and WDQS).
+ *
+ * This algorithm will act on each rank in each channel separately.
+ */
+void wr_level(struct mrc_params *mrc_params)
+{
+	uint8_t ch;	/* channel counter */
+	uint8_t rk;	/* rank counter */
+	uint8_t bl;	/* byte lane counter */
+	uint8_t bl_divisor = (mrc_params->channel_width == X16) ? 2 : 1;
+
+#ifdef R2R_SHARING
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t final_delay[NUM_CHANNELS][NUM_BYTE_LANES];
+#ifndef BACKUP_WDQS
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t num_ranks_enabled = 0;
+#endif
+#endif
+
+#ifdef BACKUP_WDQS
+#else
+	/* determines stop condition for CRS_WR_LVL */
+	bool all_edges_found;
+	/* absolute PI value to be programmed on the byte lane */
+	uint32_t delay[NUM_BYTE_LANES];
+	/*
+	 * static makes it so the data is loaded in the heap once by shadow(),
+	 * where non-static copies the data onto the stack every time this
+	 * function is called
+	 */
+	uint32_t address;	/* address to be checked during COARSE_WR_LVL */
+	u32 dtr4, dtr4_save;
+#endif
+
+	ENTERFN();
+
+	/* wr_level starts */
+	mrc_post_code(0x06, 0x00);
+
+#ifdef R2R_SHARING
+	/* need to set "final_delay[][]" elements to "0" */
+	memset((void *)(final_delay), 0x00, (size_t)sizeof(final_delay));
+#endif
+
+	/* loop through each enabled channel */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			/* perform WRITE LEVELING algorithm on a per rank basis */
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+					/*
+					 * POST_CODE here indicates the current
+					 * rank and channel being calibrated
+					 */
+					mrc_post_code(0x06, (0x10 + ((ch << 4) | rk)));
+
+#ifdef BACKUP_WDQS
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						set_wdqs(ch, rk, bl, ddr_wdqs[PLATFORM_ID]);
+						set_wdq(ch, rk, bl, (ddr_wdqs[PLATFORM_ID] - QRTR_CLK));
+					}
+#else
+					/*
+					 * perform a single PRECHARGE_ALL command to
+					 * make DRAM state machine go to IDLE state
+					 */
+					dram_init_command(DCMD_PREA(rk));
+
+					/*
+					 * enable Write Levelling Mode
+					 * (EMRS1 w/ Write Levelling Mode Enable)
+					 */
+					dram_init_command(DCMD_MRS1(rk, 0x0082));
+
+					/*
+					 * set ODT DRAM Full Time Termination
+					 * disable in MCU
+					 */
+
+					dtr4 = msg_port_read(MEM_CTLR, DTR4);
+					dtr4_save = dtr4;
+					dtr4 |= BIT15;
+					msg_port_write(MEM_CTLR, DTR4, dtr4);
+
+					for (bl = 0; bl < ((NUM_BYTE_LANES / bl_divisor) / 2); bl++) {
+						/*
+						 * Enable Sandy Bridge Mode (WDQ Tri-State) &
+						 * Ensure 5 WDQS pulses during Write Leveling
+						 */
+						mrc_alt_write_mask(DDRPHY,
+							DQCTL + (DDRIODQ_BL_OFFSET * bl) + (DDRIODQ_CH_OFFSET * ch),
+							(BIT28 | BIT8 | BIT6 | BIT4 | BIT2),
+							(BIT28 | BIT9 | BIT8 | BIT7 | BIT6 | BIT5 | BIT4 | BIT3 | BIT2));
+					}
+
+					/* Write Leveling Mode enabled in IO */
+					mrc_alt_write_mask(DDRPHY,
+						CCDDR3RESETCTL + (DDRIOCCC_CH_OFFSET * ch),
+						BIT16, BIT16);
+
+					/* Initialize the starting delay to WCLK */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						/*
+						 * CLK0 --> RK0
+						 * CLK1 --> RK1
+						 */
+						delay[bl] = get_wclk(ch, rk);
+
+						set_wdqs(ch, rk, bl, delay[bl]);
+					}
+
+					/* now find the rising edge */
+					find_rising_edge(mrc_params, delay, ch, rk, false);
+
+					/* disable Write Levelling Mode */
+					mrc_alt_write_mask(DDRPHY,
+						CCDDR3RESETCTL + (DDRIOCCC_CH_OFFSET * ch),
+						0, BIT16);
+
+					for (bl = 0; bl < ((NUM_BYTE_LANES / bl_divisor) / 2); bl++) {
+						/* Disable Sandy Bridge Mode & Ensure 4 WDQS pulses during normal operation */
+						mrc_alt_write_mask(DDRPHY,
+							DQCTL + (DDRIODQ_BL_OFFSET * bl) + (DDRIODQ_CH_OFFSET * ch),
+							(BIT8 | BIT6 | BIT4 | BIT2),
+							(BIT28 | BIT9 | BIT8 | BIT7 | BIT6 | BIT5 | BIT4 | BIT3 | BIT2));
+					}
+
+					/* restore original DTR4 */
+					msg_port_write(MEM_CTLR, DTR4, dtr4_save);
+
+					/*
+					 * restore original value
+					 * (Write Levelling Mode Disable)
+					 */
+					dram_init_command(DCMD_MRS1(rk, mrc_params->mrs1));
+
+					/*
+					 * perform a single PRECHARGE_ALL command to
+					 * make DRAM state machine go to IDLE state
+					 */
+					dram_init_command(DCMD_PREA(rk));
+
+					mrc_post_code(0x06, (0x30 + ((ch << 4) | rk)));
+
+					/*
+					 * COARSE WRITE LEVEL:
+					 * check that we're on the correct clock edge
+					 */
+
+					/* hte reconfiguration request */
+					mrc_params->hte_setup = 1;
+
+					/* start CRS_WR_LVL with WDQS = WDQS + 128 PI */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						delay[bl] = get_wdqs(ch, rk, bl) + FULL_CLK;
+						set_wdqs(ch, rk, bl, delay[bl]);
+						/*
+						 * program WDQ timings based on WDQS
+						 * (WDQ = WDQS - 32 PI)
+						 */
+						set_wdq(ch, rk, bl, (delay[bl] - QRTR_CLK));
+					}
+
+					/* get an address in the targeted channel/rank */
+					address = get_addr(ch, rk);
+					do {
+						uint32_t coarse_result = 0x00;
+						uint32_t coarse_result_mask = byte_lane_mask(mrc_params);
+						/* assume pass */
+						all_edges_found = true;
+
+						mrc_params->hte_setup = 1;
+						coarse_result = check_rw_coarse(mrc_params, address);
+
+						/* check for failures and margin the byte lane back 128 PI (1 CLK) */
+						for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+							if (coarse_result & (coarse_result_mask << bl)) {
+								all_edges_found = false;
+								delay[bl] -= FULL_CLK;
+								set_wdqs(ch, rk, bl, delay[bl]);
+								/* program WDQ timings based on WDQS (WDQ = WDQS - 32 PI) */
+								set_wdq(ch, rk, bl, (delay[bl] - QRTR_CLK));
+							}
+						}
+					} while (!all_edges_found);
+
+#ifdef R2R_SHARING
+					/* increment "num_ranks_enabled" */
+					 num_ranks_enabled++;
+					/* accumulate "final_delay[][]" values from "delay[]" values for rolling average */
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						final_delay[ch][bl] += delay[bl];
+						set_wdqs(ch, rk, bl, ((final_delay[ch][bl]) / num_ranks_enabled));
+						/* program WDQ timings based on WDQS (WDQ = WDQS - 32 PI) */
+						set_wdq(ch, rk, bl, ((final_delay[ch][bl]) / num_ranks_enabled) - QRTR_CLK);
+					}
+#endif
+#endif
+				}
+			}
+		}
+	}
+
+	LEAVEFN();
+}
+
+void prog_page_ctrl(struct mrc_params *mrc_params)
+{
+	u32 dpmc0;
+
+	ENTERFN();
+
+	dpmc0 = msg_port_read(MEM_CTLR, DPMC0);
+	dpmc0 &= ~(BIT16 | BIT17 | BIT18);
+	dpmc0 |= (4 << 16);
+	dpmc0 |= BIT21;
+	msg_port_write(MEM_CTLR, DPMC0, dpmc0);
+}
+
+/*
+ * This function will perform the READ TRAINING Algorithm on all
+ * channels/ranks/byte_lanes simultaneously to minimize execution time.
+ *
+ * The idea here is to train the VREF and RDQS (and eventually RDQ) values
+ * to achieve maximum READ margins. The algorithm will first determine the
+ * X coordinate (RDQS setting). This is done by collapsing the VREF eye
+ * until we find a minimum required RDQS eye for VREF_MIN and VREF_MAX.
+ * Then we take the averages of the RDQS eye at VREF_MIN and VREF_MAX,
+ * then average those; this will be the final X coordinate. The algorithm
+ * will then determine the Y coordinate (VREF setting). This is done by
+ * collapsing the RDQS eye until we find a minimum required VREF eye for
+ * RDQS_MIN and RDQS_MAX. Then we take the averages of the VREF eye at
+ * RDQS_MIN and RDQS_MAX, then average those; this will be the final Y
+ * coordinate.
+ *
+ * NOTE: this algorithm assumes the eye curves have a one-to-one relationship,
+ * meaning for each X the curve has only one Y and vice-a-versa.
+ */
+void rd_train(struct mrc_params *mrc_params)
+{
+	uint8_t ch;	/* channel counter */
+	uint8_t rk;	/* rank counter */
+	uint8_t bl;	/* byte lane counter */
+	uint8_t bl_divisor = (mrc_params->channel_width == X16) ? 2 : 1;
+#ifdef BACKUP_RDQS
+#else
+	uint8_t side_x;	/* tracks LEFT/RIGHT approach vectors */
+	uint8_t side_y;	/* tracks BOTTOM/TOP approach vectors */
+	/* X coordinate data (passing RDQS values) for approach vectors */
+	uint8_t x_coordinate[2][2][NUM_CHANNELS][NUM_RANKS][NUM_BYTE_LANES];
+	/* Y coordinate data (passing VREF values) for approach vectors */
+	uint8_t y_coordinate[2][2][NUM_CHANNELS][NUM_BYTE_LANES];
+	/* centered X (RDQS) */
+	uint8_t x_center[NUM_CHANNELS][NUM_RANKS][NUM_BYTE_LANES];
+	/* centered Y (VREF) */
+	uint8_t y_center[NUM_CHANNELS][NUM_BYTE_LANES];
+	uint32_t address;	/* target address for check_bls_ex() */
+	uint32_t result;	/* result of check_bls_ex() */
+	uint32_t bl_mask;	/* byte lane mask for result checking */
+#ifdef R2R_SHARING
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t final_delay[NUM_CHANNELS][NUM_BYTE_LANES];
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t num_ranks_enabled = 0;
+#endif
+#endif
+
+	/* rd_train starts */
+	mrc_post_code(0x07, 0x00);
+
+	ENTERFN();
+
+#ifdef BACKUP_RDQS
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+					for (bl = 0;
+					     bl < (NUM_BYTE_LANES / bl_divisor);
+					     bl++) {
+						set_rdqs(ch, rk, bl, ddr_rdqs[PLATFORM_ID]);
+					}
+				}
+			}
+		}
+	}
+#else
+	/* initialize x/y_coordinate arrays */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+					for (bl = 0;
+					     bl < (NUM_BYTE_LANES / bl_divisor);
+					     bl++) {
+						/* x_coordinate */
+						x_coordinate[L][B][ch][rk][bl] = RDQS_MIN;
+						x_coordinate[R][B][ch][rk][bl] = RDQS_MAX;
+						x_coordinate[L][T][ch][rk][bl] = RDQS_MIN;
+						x_coordinate[R][T][ch][rk][bl] = RDQS_MAX;
+						/* y_coordinate */
+						y_coordinate[L][B][ch][bl] = VREF_MIN;
+						y_coordinate[R][B][ch][bl] = VREF_MIN;
+						y_coordinate[L][T][ch][bl] = VREF_MAX;
+						y_coordinate[R][T][ch][bl] = VREF_MAX;
+					}
+				}
+			}
+		}
+	}
+
+	/* initialize other variables */
+	bl_mask = byte_lane_mask(mrc_params);
+	address = get_addr(0, 0);
+
+#ifdef R2R_SHARING
+	/* need to set "final_delay[][]" elements to "0" */
+	memset((void *)(final_delay), 0x00, (size_t)sizeof(final_delay));
+#endif
+
+	/* look for passing coordinates */
+	for (side_y = B; side_y <= T; side_y++) {
+		for (side_x = L; side_x <= R; side_x++) {
+			mrc_post_code(0x07, (0x10 + (side_y * 2) + (side_x)));
+
+			/* find passing values */
+			for (ch = 0; ch < NUM_CHANNELS; ch++) {
+				if (mrc_params->channel_enables & (0x1 << ch)) {
+					for (rk = 0; rk < NUM_RANKS; rk++) {
+						if (mrc_params->rank_enables &
+							(0x1 << rk)) {
+							/* set x/y_coordinate search starting settings */
+							for (bl = 0;
+							     bl < (NUM_BYTE_LANES / bl_divisor);
+							     bl++) {
+								set_rdqs(ch, rk, bl,
+									 x_coordinate[side_x][side_y][ch][rk][bl]);
+								set_vref(ch, bl,
+									 y_coordinate[side_x][side_y][ch][bl]);
+							}
+
+							/* get an address in the target channel/rank */
+							address = get_addr(ch, rk);
+
+							/* request HTE reconfiguration */
+							mrc_params->hte_setup = 1;
+
+							/* test the settings */
+							do {
+								/* result[07:00] == failing byte lane (MAX 8) */
+								result = check_bls_ex(mrc_params, address);
+
+								/* check for failures */
+								if (result & 0xFF) {
+									/* at least 1 byte lane failed */
+									for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+										if (result &
+											(bl_mask << bl)) {
+											/* adjust the RDQS values accordingly */
+											if (side_x == L)
+												x_coordinate[L][side_y][ch][rk][bl] += RDQS_STEP;
+											else
+												x_coordinate[R][side_y][ch][rk][bl] -= RDQS_STEP;
+
+											/* check that we haven't closed the RDQS_EYE too much */
+											if ((x_coordinate[L][side_y][ch][rk][bl] > (RDQS_MAX - MIN_RDQS_EYE)) ||
+												(x_coordinate[R][side_y][ch][rk][bl] < (RDQS_MIN + MIN_RDQS_EYE)) ||
+												(x_coordinate[L][side_y][ch][rk][bl] ==
+												x_coordinate[R][side_y][ch][rk][bl])) {
+												/*
+												 * not enough RDQS margin available at this VREF
+												 * update VREF values accordingly
+												 */
+												if (side_y == B)
+													y_coordinate[side_x][B][ch][bl] += VREF_STEP;
+												else
+													y_coordinate[side_x][T][ch][bl] -= VREF_STEP;
+
+												/* check that we haven't closed the VREF_EYE too much */
+												if ((y_coordinate[side_x][B][ch][bl] > (VREF_MAX - MIN_VREF_EYE)) ||
+													(y_coordinate[side_x][T][ch][bl] < (VREF_MIN + MIN_VREF_EYE)) ||
+													(y_coordinate[side_x][B][ch][bl] == y_coordinate[side_x][T][ch][bl])) {
+													/* VREF_EYE collapsed below MIN_VREF_EYE */
+													training_message(ch, rk, bl);
+													mrc_post_code(0xEE, (0x70 + (side_y * 2) + (side_x)));
+												} else {
+													/* update the VREF setting */
+													set_vref(ch, bl, y_coordinate[side_x][side_y][ch][bl]);
+													/* reset the X coordinate to begin the search at the new VREF */
+													x_coordinate[side_x][side_y][ch][rk][bl] =
+														(side_x == L) ? (RDQS_MIN) : (RDQS_MAX);
+												}
+											}
+
+											/* update the RDQS setting */
+											set_rdqs(ch, rk, bl, x_coordinate[side_x][side_y][ch][rk][bl]);
+										}
+									}
+								}
+							} while (result & 0xFF);
+						}
+					}
+				}
+			}
+		}
+	}
+
+	mrc_post_code(0x07, 0x20);
+
+	/* find final RDQS (X coordinate) & final VREF (Y coordinate) */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						uint32_t temp1;
+						uint32_t temp2;
+
+						/* x_coordinate */
+						DPF(D_INFO,
+						    "RDQS T/B eye rank%d lane%d : %d-%d %d-%d\n",
+						    rk, bl,
+						    x_coordinate[L][T][ch][rk][bl],
+						    x_coordinate[R][T][ch][rk][bl],
+						    x_coordinate[L][B][ch][rk][bl],
+						    x_coordinate[R][B][ch][rk][bl]);
+
+						/* average the TOP side LEFT & RIGHT values */
+						temp1 = (x_coordinate[R][T][ch][rk][bl] + x_coordinate[L][T][ch][rk][bl]) / 2;
+						/* average the BOTTOM side LEFT & RIGHT values */
+						temp2 = (x_coordinate[R][B][ch][rk][bl] + x_coordinate[L][B][ch][rk][bl]) / 2;
+						/* average the above averages */
+						x_center[ch][rk][bl] = (uint8_t) ((temp1 + temp2) / 2);
+
+						/* y_coordinate */
+						DPF(D_INFO,
+						    "VREF R/L eye lane%d : %d-%d %d-%d\n",
+						    bl,
+						    y_coordinate[R][B][ch][bl],
+						    y_coordinate[R][T][ch][bl],
+						    y_coordinate[L][B][ch][bl],
+						    y_coordinate[L][T][ch][bl]);
+
+						/* average the RIGHT side TOP & BOTTOM values */
+						temp1 = (y_coordinate[R][T][ch][bl] + y_coordinate[R][B][ch][bl]) / 2;
+						/* average the LEFT side TOP & BOTTOM values */
+						temp2 = (y_coordinate[L][T][ch][bl] + y_coordinate[L][B][ch][bl]) / 2;
+						/* average the above averages */
+						y_center[ch][bl] = (uint8_t) ((temp1 + temp2) / 2);
+					}
+				}
+			}
+		}
+	}
+
+#ifdef RX_EYE_CHECK
+	/* perform an eye check */
+	for (side_y = B; side_y <= T; side_y++) {
+		for (side_x = L; side_x <= R; side_x++) {
+			mrc_post_code(0x07, (0x30 + (side_y * 2) + (side_x)));
+
+			/* update the settings for the eye check */
+			for (ch = 0; ch < NUM_CHANNELS; ch++) {
+				if (mrc_params->channel_enables & (1 << ch)) {
+					for (rk = 0; rk < NUM_RANKS; rk++) {
+						if (mrc_params->rank_enables & (1 << rk)) {
+							for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+								if (side_x == L)
+									set_rdqs(ch, rk, bl, (x_center[ch][rk][bl] - (MIN_RDQS_EYE / 2)));
+								else
+									set_rdqs(ch, rk, bl, (x_center[ch][rk][bl] + (MIN_RDQS_EYE / 2)));
+
+								if (side_y == B)
+									set_vref(ch, bl, (y_center[ch][bl] - (MIN_VREF_EYE / 2)));
+								else
+									set_vref(ch, bl, (y_center[ch][bl] + (MIN_VREF_EYE / 2)));
+							}
+						}
+					}
+				}
+			}
+
+			/* request HTE reconfiguration */
+			mrc_params->hte_setup = 1;
+
+			/* check the eye */
+			if (check_bls_ex(mrc_params, address) & 0xFF) {
+				/* one or more byte lanes failed */
+				mrc_post_code(0xEE, (0x74 + (side_x * 2) + (side_y)));
+			}
+		}
+	}
+#endif
+
+	mrc_post_code(0x07, 0x40);
+
+	/* set final placements */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+#ifdef R2R_SHARING
+					/* increment "num_ranks_enabled" */
+					num_ranks_enabled++;
+#endif
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						/* x_coordinate */
+#ifdef R2R_SHARING
+						final_delay[ch][bl] += x_center[ch][rk][bl];
+						set_rdqs(ch, rk, bl, ((final_delay[ch][bl]) / num_ranks_enabled));
+#else
+						set_rdqs(ch, rk, bl, x_center[ch][rk][bl]);
+#endif
+						/* y_coordinate */
+						set_vref(ch, bl, y_center[ch][bl]);
+					}
+				}
+			}
+		}
+	}
+#endif
+
+	LEAVEFN();
+}
+
+/*
+ * This function will perform the WRITE TRAINING Algorithm on all
+ * channels/ranks/byte_lanes simultaneously to minimize execution time.
+ *
+ * The idea here is to train the WDQ timings to achieve maximum WRITE margins.
+ * The algorithm will start with WDQ at the current WDQ setting (tracks WDQS
+ * in WR_LVL) +/- 32 PIs (+/- 1/4 CLK) and collapse the eye until all data
+ * patterns pass. This is because WDQS will be aligned to WCLK by the
+ * Write Leveling algorithm and WDQ will only ever have a 1/2 CLK window
+ * of validity.
+ */
+void wr_train(struct mrc_params *mrc_params)
+{
+	uint8_t ch;	/* channel counter */
+	uint8_t rk;	/* rank counter */
+	uint8_t bl;	/* byte lane counter */
+	uint8_t bl_divisor = (mrc_params->channel_width == X16) ? 2 : 1;
+#ifdef BACKUP_WDQ
+#else
+	uint8_t side;		/* LEFT/RIGHT side indicator (0=L, 1=R) */
+	uint32_t temp;		/* temporary DWORD */
+	/* 2 arrays, for L & R side passing delays */
+	uint32_t delay[2][NUM_CHANNELS][NUM_RANKS][NUM_BYTE_LANES];
+	uint32_t address;	/* target address for check_bls_ex() */
+	uint32_t result;	/* result of check_bls_ex() */
+	uint32_t bl_mask;	/* byte lane mask for result checking */
+#ifdef R2R_SHARING
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t final_delay[NUM_CHANNELS][NUM_BYTE_LANES];
+	/* used to find placement for rank2rank sharing configs */
+	uint32_t num_ranks_enabled = 0;
+#endif
+#endif
+
+	/* wr_train starts */
+	mrc_post_code(0x08, 0x00);
+
+	ENTERFN();
+
+#ifdef BACKUP_WDQ
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+					for (bl = 0;
+					     bl < (NUM_BYTE_LANES / bl_divisor);
+					     bl++) {
+						set_wdq(ch, rk, bl, ddr_wdq[PLATFORM_ID]);
+					}
+				}
+			}
+		}
+	}
+#else
+	/* initialize "delay" */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+					for (bl = 0;
+					     bl < (NUM_BYTE_LANES / bl_divisor);
+					     bl++) {
+						/*
+						 * want to start with
+						 * WDQ = (WDQS - QRTR_CLK)
+						 * +/- QRTR_CLK
+						 */
+						temp = get_wdqs(ch, rk, bl) - QRTR_CLK;
+						delay[L][ch][rk][bl] = temp - QRTR_CLK;
+						delay[R][ch][rk][bl] = temp + QRTR_CLK;
+					}
+				}
+			}
+		}
+	}
+
+	/* initialize other variables */
+	bl_mask = byte_lane_mask(mrc_params);
+	address = get_addr(0, 0);
+
+#ifdef R2R_SHARING
+	/* need to set "final_delay[][]" elements to "0" */
+	memset((void *)(final_delay), 0x00, (size_t)sizeof(final_delay));
+#endif
+
+	/*
+	 * start algorithm on the LEFT side and train each channel/bl
+	 * until no failures are observed, then repeat for the RIGHT side.
+	 */
+	for (side = L; side <= R; side++) {
+		mrc_post_code(0x08, (0x10 + (side)));
+
+		/* set starting values */
+		for (ch = 0; ch < NUM_CHANNELS; ch++) {
+			if (mrc_params->channel_enables & (1 << ch)) {
+				for (rk = 0; rk < NUM_RANKS; rk++) {
+					if (mrc_params->rank_enables &
+						(1 << rk)) {
+						for (bl = 0;
+						     bl < (NUM_BYTE_LANES / bl_divisor);
+						     bl++) {
+							set_wdq(ch, rk, bl, delay[side][ch][rk][bl]);
+						}
+					}
+				}
+			}
+		}
+
+		/* find passing values */
+		for (ch = 0; ch < NUM_CHANNELS; ch++) {
+			if (mrc_params->channel_enables & (1 << ch)) {
+				for (rk = 0; rk < NUM_RANKS; rk++) {
+					if (mrc_params->rank_enables &
+						(1 << rk)) {
+						/* get an address in the target channel/rank */
+						address = get_addr(ch, rk);
+
+						/* request HTE reconfiguration */
+						mrc_params->hte_setup = 1;
+
+						/* check the settings */
+						do {
+							/* result[07:00] == failing byte lane (MAX 8) */
+							result = check_bls_ex(mrc_params, address);
+							/* check for failures */
+							if (result & 0xFF) {
+								/* at least 1 byte lane failed */
+								for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+									if (result &
+										(bl_mask << bl)) {
+										if (side == L)
+											delay[L][ch][rk][bl] += WDQ_STEP;
+										else
+											delay[R][ch][rk][bl] -= WDQ_STEP;
+
+										/* check for algorithm failure */
+										if (delay[L][ch][rk][bl] != delay[R][ch][rk][bl]) {
+											/*
+											 * margin available
+											 * update delay setting
+											 */
+											set_wdq(ch, rk, bl,
+												delay[side][ch][rk][bl]);
+										} else {
+											/*
+											 * no margin available
+											 * notify the user and halt
+											 */
+											training_message(ch, rk, bl);
+											mrc_post_code(0xEE, (0x80 + side));
+										}
+									}
+								}
+							}
+						/* stop when all byte lanes pass */
+						} while (result & 0xFF);
+					}
+				}
+			}
+		}
+	}
+
+	/* program WDQ to the middle of passing window */
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		if (mrc_params->channel_enables & (1 << ch)) {
+			for (rk = 0; rk < NUM_RANKS; rk++) {
+				if (mrc_params->rank_enables & (1 << rk)) {
+#ifdef R2R_SHARING
+					/* increment "num_ranks_enabled" */
+					num_ranks_enabled++;
+#endif
+					for (bl = 0; bl < (NUM_BYTE_LANES / bl_divisor); bl++) {
+						DPF(D_INFO,
+						    "WDQ eye rank%d lane%d : %d-%d\n",
+						    rk, bl,
+						    delay[L][ch][rk][bl],
+						    delay[R][ch][rk][bl]);
+
+						temp = (delay[R][ch][rk][bl] + delay[L][ch][rk][bl]) / 2;
+
+#ifdef R2R_SHARING
+						final_delay[ch][bl] += temp;
+						set_wdq(ch, rk, bl,
+							((final_delay[ch][bl]) / num_ranks_enabled));
+#else
+						set_wdq(ch, rk, bl, temp);
+#endif
+					}
+				}
+			}
+		}
+	}
+#endif
+
+	LEAVEFN();
+}
+
+/*
+ * This function will store relevant timing data
+ *
+ * This data will be used on subsequent boots to speed up boot times
+ * and is required for Suspend To RAM capabilities.
+ */
+void store_timings(struct mrc_params *mrc_params)
+{
+	uint8_t ch, rk, bl;
+	struct mrc_timings *mt = &mrc_params->timings;
+
+	for (ch = 0; ch < NUM_CHANNELS; ch++) {
+		for (rk = 0; rk < NUM_RANKS; rk++) {
+			for (bl = 0; bl < NUM_BYTE_LANES; bl++) {
+				mt->rcvn[ch][rk][bl] = get_rcvn(ch, rk, bl);
+				mt->rdqs[ch][rk][bl] = get_rdqs(ch, rk, bl);
+				mt->wdqs[ch][rk][bl] = get_wdqs(ch, rk, bl);
+				mt->wdq[ch][rk][bl] = get_wdq(ch, rk, bl);
+
+				if (rk == 0)
+					mt->vref[ch][bl] = get_vref(ch, bl);
+			}
+
+			mt->wctl[ch][rk] = get_wctl(ch, rk);
+		}
+
+		mt->wcmd[ch] = get_wcmd(ch);
+	}
+
+	/* need to save for a case of changing frequency after warm reset */
+	mt->ddr_speed = mrc_params->ddr_speed;
+}
+
+/*
+ * The purpose of this function is to ensure the SEC comes out of reset
+ * and IA initiates the SEC enabling Memory Scrambling.
+ */
+void enable_scrambling(struct mrc_params *mrc_params)
+{
+	uint32_t lfsr = 0;
+	uint8_t i;
+
+	if (mrc_params->scrambling_enables == 0)
+		return;
+
+	ENTERFN();
+
+	/* 32 bit seed is always stored in BIOS NVM */
+	lfsr = mrc_params->timings.scrambler_seed;
+
+	if (mrc_params->boot_mode == BM_COLD) {
+		/*
+		 * factory value is 0 and in first boot,
+		 * a clock based seed is loaded.
+		 */
+		if (lfsr == 0) {
+			/*
+			 * get seed from system clock
+			 * and make sure it is not all 1's
+			 */
+			lfsr = rdtsc() & 0x0FFFFFFF;
+		} else {
+			/*
+			 * Need to replace scrambler
+			 *
+			 * get next 32bit LFSR 16 times which is the last
+			 * part of the previous scrambler vector
+			 */
+			for (i = 0; i < 16; i++)
+				lfsr32(&lfsr);
+		}
+
+		/* save new seed */
+		mrc_params->timings.scrambler_seed = lfsr;
+	}
+
+	/*
+	 * In warm boot or S3 exit, we have the previous seed.
+	 * In cold boot, we have the last 32bit LFSR which is the new seed.
+	 */
+	lfsr32(&lfsr);	/* shift to next value */
+	msg_port_write(MEM_CTLR, SCRMSEED, (lfsr & 0x0003FFFF));
+
+	for (i = 0; i < 2; i++)
+		msg_port_write(MEM_CTLR, SCRMLO + i, (lfsr & 0xAAAAAAAA));
+
+	LEAVEFN();
+}
+
+/*
+ * Configure MCU Power Management Control Register
+ * and Scheduler Control Register
+ */
+void prog_ddr_control(struct mrc_params *mrc_params)
+{
+	u32 dsch;
+	u32 dpmc0;
+
+	ENTERFN();
+
+	dsch = msg_port_read(MEM_CTLR, DSCH);
+	dsch &= ~(BIT8 | BIT9 | BIT12);
+	msg_port_write(MEM_CTLR, DSCH, dsch);
+
+	dpmc0 = msg_port_read(MEM_CTLR, DPMC0);
+	dpmc0 &= ~BIT25;
+	dpmc0 |= (mrc_params->power_down_disable << 25);
+	dpmc0 &= ~BIT24;
+	dpmc0 &= ~(BIT16 | BIT17 | BIT18);
+	dpmc0 |= (4 << 16);
+	dpmc0 |= BIT21;
+	msg_port_write(MEM_CTLR, DPMC0, dpmc0);
+
+	/* CMDTRIST = 2h - CMD/ADDR are tristated when no valid command */
+	mrc_write_mask(MEM_CTLR, DPMC1, 2 << 4, BIT4 | BIT5);
+
+	LEAVEFN();
+}
+
+/*
+ * After training complete configure MCU Rank Population Register
+ * specifying: ranks enabled, device width, density, address mode
+ */
+void prog_dra_drb(struct mrc_params *mrc_params)
+{
+	u32 drp;
+	u32 dco;
+	u8 density = mrc_params->params.density;
+
+	ENTERFN();
+
+	dco = msg_port_read(MEM_CTLR, DCO);
+	dco &= ~BIT31;
+	msg_port_write(MEM_CTLR, DCO, dco);
+
+	drp = 0;
+	if (mrc_params->rank_enables & 1)
+		drp |= BIT0;
+	if (mrc_params->rank_enables & 2)
+		drp |= BIT1;
+	if (mrc_params->dram_width == X16) {
+		drp |= (1 << 4);
+		drp |= (1 << 9);
+	}
+
+	/*
+	 * Density encoding in struct dram_params: 0=512Mb, 1=Gb, 2=2Gb, 3=4Gb
+	 * has to be mapped RANKDENSx encoding (0=1Gb)
+	 */
+	if (density == 0)
+		density = 4;
+
+	drp |= ((density - 1) << 6);
+	drp |= ((density - 1) << 11);
+
+	/* Address mode can be overwritten if ECC enabled */
+	drp |= (mrc_params->address_mode << 14);
+
+	msg_port_write(MEM_CTLR, DRP, drp);
+
+	dco &= ~BIT28;
+	dco |= BIT31;
+	msg_port_write(MEM_CTLR, DCO, dco);
+
+	LEAVEFN();
+}
+
+/* Send DRAM wake command */
+void perform_wake(struct mrc_params *mrc_params)
+{
+	ENTERFN();
+
+	dram_wake_command();
+
+	LEAVEFN();
+}
+
+/*
+ * Configure refresh rate and short ZQ calibration interval
+ * Activate dynamic self refresh
+ */
+void change_refresh_period(struct mrc_params *mrc_params)
+{
+	u32 drfc;
+	u32 dcal;
+	u32 dpmc0;
+
+	ENTERFN();
+
+	drfc = msg_port_read(MEM_CTLR, DRFC);
+	drfc &= ~(BIT12 | BIT13 | BIT14);
+	drfc |= (mrc_params->refresh_rate << 12);
+	drfc |= BIT21;
+	msg_port_write(MEM_CTLR, DRFC, drfc);
+
+	dcal = msg_port_read(MEM_CTLR, DCAL);
+	dcal &= ~(BIT8 | BIT9 | BIT10);
+	dcal |= (3 << 8);	/* 63ms */
+	msg_port_write(MEM_CTLR, DCAL, dcal);
+
+	dpmc0 = msg_port_read(MEM_CTLR, DPMC0);
+	dpmc0 |= (BIT23 | BIT29);
+	msg_port_write(MEM_CTLR, DPMC0, dpmc0);
+
+	LEAVEFN();
+}
+
+/*
+ * Configure DDRPHY for Auto-Refresh, Periodic Compensations,
+ * Dynamic Diff-Amp, ZQSPERIOD, Auto-Precharge, CKE Power-Down
+ */
+void set_auto_refresh(struct mrc_params *mrc_params)
+{
+	uint32_t channel;
+	uint32_t rank;
+	uint32_t bl;
+	uint32_t bl_divisor = 1;
+	uint32_t temp;
+
+	ENTERFN();
+
+	/*
+	 * Enable Auto-Refresh, Periodic Compensations, Dynamic Diff-Amp,
+	 * ZQSPERIOD, Auto-Precharge, CKE Power-Down
+	 */
+	for (channel = 0; channel < NUM_CHANNELS; channel++) {
+		if (mrc_params->channel_enables & (1 << channel)) {
+			/* Enable Periodic RCOMPS */
+			mrc_alt_write_mask(DDRPHY, CMPCTRL, BIT1, BIT1);
+
+			/* Enable Dynamic DiffAmp & Set Read ODT Value */
+			switch (mrc_params->rd_odt_value) {
+			case 0:
+				temp = 0x3F;	/* OFF */
+				break;
+			default:
+				temp = 0x00;	/* Auto */
+				break;
+			}
+
+			for (bl = 0; bl < ((NUM_BYTE_LANES / bl_divisor) / 2); bl++) {
+				/* Override: DIFFAMP, ODT */
+				mrc_alt_write_mask(DDRPHY,
+					(B0OVRCTL + (bl * DDRIODQ_BL_OFFSET) +
+					(channel * DDRIODQ_CH_OFFSET)),
+					(0x00 << 16) | (temp << 10),
+					(BIT21 | BIT20 | BIT19 | BIT18 |
+					 BIT17 | BIT16 | BIT15 | BIT14 |
+					 BIT13 | BIT12 | BIT11 | BIT10));
+
+				/* Override: DIFFAMP, ODT */
+				mrc_alt_write_mask(DDRPHY,
+					(B1OVRCTL + (bl * DDRIODQ_BL_OFFSET) +
+					(channel * DDRIODQ_CH_OFFSET)),
+					(0x00 << 16) | (temp << 10),
+					(BIT21 | BIT20 | BIT19 | BIT18 |
+					 BIT17 | BIT16 | BIT15 | BIT14 |
+					 BIT13 | BIT12 | BIT11 | BIT10));
+			}
+
+			/* Issue ZQCS command */
+			for (rank = 0; rank < NUM_RANKS; rank++) {
+				if (mrc_params->rank_enables & (1 << rank))
+					dram_init_command(DCMD_ZQCS(rank));
+			}
+		}
+	}
+
+	clear_pointers();
+
+	LEAVEFN();
+}
+
+/*
+ * Depending on configuration enables ECC support
+ *
+ * Available memory size is decreased, and updated with 0s
+ * in order to clear error status. Address mode 2 forced.
+ */
+void ecc_enable(struct mrc_params *mrc_params)
+{
+	u32 drp;
+	u32 dsch;
+	u32 ecc_ctrl;
+
+	if (mrc_params->ecc_enables == 0)
+		return;
+
+	ENTERFN();
+
+	/* Configuration required in ECC mode */
+	drp = msg_port_read(MEM_CTLR, DRP);
+	drp &= ~(BIT14 | BIT15);
+	drp |= BIT15;
+	drp |= BIT13;
+	msg_port_write(MEM_CTLR, DRP, drp);
+
+	/* Disable new request bypass */
+	dsch = msg_port_read(MEM_CTLR, DSCH);
+	dsch |= BIT12;
+	msg_port_write(MEM_CTLR, DSCH, dsch);
+
+	/* Enable ECC */
+	ecc_ctrl = (BIT0 | BIT1 | BIT17);
+	msg_port_write(MEM_CTLR, DECCCTRL, ecc_ctrl);
+
+	/* Assume 8 bank memory, one bank is gone for ECC */
+	mrc_params->mem_size -= mrc_params->mem_size / 8;
+
+	/* For S3 resume memory content has to be preserved */
+	if (mrc_params->boot_mode != BM_S3) {
+		select_hte();
+		hte_mem_init(mrc_params, MRC_MEM_INIT);
+		select_mem_mgr();
+	}
+
+	LEAVEFN();
+}
+
+/*
+ * Execute memory test
+ * if error detected it is indicated in mrc_params->status
+ */
+void memory_test(struct mrc_params *mrc_params)
+{
+	uint32_t result = 0;
+
+	ENTERFN();
+
+	select_hte();
+	result = hte_mem_init(mrc_params, MRC_MEM_TEST);
+	select_mem_mgr();
+
+	DPF(D_INFO, "Memory test result %x\n", result);
+	mrc_params->status = ((result == 0) ? MRC_SUCCESS : MRC_E_MEMTEST);
+	LEAVEFN();
+}
+
+/* Lock MCU registers at the end of initialization sequence */
+void lock_registers(struct mrc_params *mrc_params)
+{
+	u32 dco;
+
+	ENTERFN();
+
+	dco = msg_port_read(MEM_CTLR, DCO);
+	dco &= ~(BIT28 | BIT29);
+	dco |= (BIT0 | BIT8);
+	msg_port_write(MEM_CTLR, DCO, dco);
+
+	LEAVEFN();
+}
diff --git a/arch/x86/cpu/quark/smc.h b/arch/x86/cpu/quark/smc.h
new file mode 100644
index 0000000000..46017a1ccb
--- /dev/null
+++ b/arch/x86/cpu/quark/smc.h
@@ -0,0 +1,446 @@
+/*
+ * Copyright (C) 2013, Intel Corporation
+ * Copyright (C) 2015, Bin Meng <bmeng.cn@gmail.com>
+ *
+ * Ported from Intel released Quark UEFI BIOS
+ * QuarkSocPkg/QuarkNorthCluster/MemoryInit/Pei
+ *
+ * SPDX-License-Identifier:	Intel
+ */
+
+#ifndef _SMC_H_
+#define _SMC_H_
+
+/* System Memory Controller Register Defines */
+
+/* Memory Controller Message Bus Registers Offsets */
+#define DRP			0x00
+#define DTR0			0x01
+#define DTR1			0x02
+#define DTR2			0x03
+#define DTR3			0x04
+#define DTR4			0x05
+#define DPMC0			0x06
+#define DPMC1			0x07
+#define DRFC			0x08
+#define DSCH			0x09
+#define DCAL			0x0A
+#define DRMC			0x0B
+#define PMSTS			0x0C
+#define DCO			0x0F
+#define DSTAT			0x20
+#define SSKPD0			0x4A
+#define SSKPD1			0x4B
+#define DECCCTRL		0x60
+#define DECCSTAT		0x61
+#define DECCSBECNT		0x62
+#define DECCSBECA		0x68
+#define DECCSBECS		0x69
+#define DECCDBECA		0x6A
+#define DECCDBECS		0x6B
+#define DFUSESTAT		0x70
+#define SCRMSEED		0x80
+#define SCRMLO			0x81
+#define SCRMHI			0x82
+
+/* DRAM init command */
+#define DCMD_MRS1(rnk, dat)	(0 | ((rnk) << 22) | (1 << 3) | ((dat) << 6))
+#define DCMD_REF(rnk)		(1 | ((rnk) << 22))
+#define DCMD_PRE(rnk)		(2 | ((rnk) << 22))
+#define DCMD_PREA(rnk)		(2 | ((rnk) << 22) | (BIT10 << 6))
+#define DCMD_ACT(rnk, row)	(3 | ((rnk) << 22) | ((row) << 6))
+#define DCMD_WR(rnk, col)	(4 | ((rnk) << 22) | ((col) << 6))
+#define DCMD_RD(rnk, col)	(5 | ((rnk) << 22) | ((col) << 6))
+#define DCMD_ZQCS(rnk)		(6 | ((rnk) << 22))
+#define DCMD_ZQCL(rnk)		(6 | ((rnk) << 22) | (BIT10 << 6))
+#define DCMD_NOP(rnk)		(7 | ((rnk) << 22))
+
+#define DDR3_EMRS1_DIC_40	(0)
+#define DDR3_EMRS1_DIC_34	(1)
+
+#define DDR3_EMRS1_RTTNOM_0	(0)
+#define DDR3_EMRS1_RTTNOM_60	(0x04)
+#define DDR3_EMRS1_RTTNOM_120	(0x40)
+#define DDR3_EMRS1_RTTNOM_40	(0x44)
+#define DDR3_EMRS1_RTTNOM_20	(0x200)
+#define DDR3_EMRS1_RTTNOM_30	(0x204)
+
+#define DDR3_EMRS2_RTTWR_60	(1 << 9)
+#define DDR3_EMRS2_RTTWR_120	(1 << 10)
+
+/* BEGIN DDRIO Registers */
+
+/* DDR IOs & COMPs */
+#define DDRIODQ_BL_OFFSET	0x0800
+#define DDRIODQ_CH_OFFSET	((NUM_BYTE_LANES / 2) * DDRIODQ_BL_OFFSET)
+#define DDRIOCCC_CH_OFFSET	0x0800
+#define DDRCOMP_CH_OFFSET	0x0100
+
+/* CH0-BL01-DQ */
+#define DQOBSCKEBBCTL		0x0000
+#define DQDLLTXCTL		0x0004
+#define DQDLLRXCTL		0x0008
+#define DQMDLLCTL		0x000C
+#define B0RXIOBUFCTL		0x0010
+#define B0VREFCTL		0x0014
+#define B0RXOFFSET1		0x0018
+#define B0RXOFFSET0		0x001C
+#define B1RXIOBUFCTL		0x0020
+#define B1VREFCTL		0x0024
+#define B1RXOFFSET1		0x0028
+#define B1RXOFFSET0		0x002C
+#define DQDFTCTL		0x0030
+#define DQTRAINSTS		0x0034
+#define B1DLLPICODER0		0x0038
+#define B0DLLPICODER0		0x003C
+#define B1DLLPICODER1		0x0040
+#define B0DLLPICODER1		0x0044
+#define B1DLLPICODER2		0x0048
+#define B0DLLPICODER2		0x004C
+#define B1DLLPICODER3		0x0050
+#define B0DLLPICODER3		0x0054
+#define B1RXDQSPICODE		0x0058
+#define B0RXDQSPICODE		0x005C
+#define B1RXDQPICODER32		0x0060
+#define B1RXDQPICODER10		0x0064
+#define B0RXDQPICODER32		0x0068
+#define B0RXDQPICODER10		0x006C
+#define B01PTRCTL0		0x0070
+#define B01PTRCTL1		0x0074
+#define B01DBCTL0		0x0078
+#define B01DBCTL1		0x007C
+#define B0LATCTL0		0x0080
+#define B1LATCTL0		0x0084
+#define B01LATCTL1		0x0088
+#define B0ONDURCTL		0x008C
+#define B1ONDURCTL		0x0090
+#define B0OVRCTL		0x0094
+#define B1OVRCTL		0x0098
+#define DQCTL			0x009C
+#define B0RK2RKCHGPTRCTRL	0x00A0
+#define B1RK2RKCHGPTRCTRL	0x00A4
+#define DQRK2RKCTL		0x00A8
+#define DQRK2RKPTRCTL		0x00AC
+#define B0RK2RKLAT		0x00B0
+#define B1RK2RKLAT		0x00B4
+#define DQCLKALIGNREG0		0x00B8
+#define DQCLKALIGNREG1		0x00BC
+#define DQCLKALIGNREG2		0x00C0
+#define DQCLKALIGNSTS0		0x00C4
+#define DQCLKALIGNSTS1		0x00C8
+#define DQCLKGATE		0x00CC
+#define B0COMPSLV1		0x00D0
+#define B1COMPSLV1		0x00D4
+#define B0COMPSLV2		0x00D8
+#define B1COMPSLV2		0x00DC
+#define B0COMPSLV3		0x00E0
+#define B1COMPSLV3		0x00E4
+#define DQVISALANECR0TOP	0x00E8
+#define DQVISALANECR1TOP	0x00EC
+#define DQVISACONTROLCRTOP	0x00F0
+#define DQVISALANECR0BL		0x00F4
+#define DQVISALANECR1BL		0x00F8
+#define DQVISACONTROLCRBL	0x00FC
+#define DQTIMINGCTRL		0x010C
+
+/* CH0-ECC */
+#define ECCDLLTXCTL		0x2004
+#define ECCDLLRXCTL		0x2008
+#define ECCMDLLCTL		0x200C
+#define ECCB1DLLPICODER0	0x2038
+#define ECCB1DLLPICODER1	0x2040
+#define ECCB1DLLPICODER2	0x2048
+#define ECCB1DLLPICODER3	0x2050
+#define ECCB01DBCTL0		0x2078
+#define ECCB01DBCTL1		0x207C
+#define ECCCLKALIGNREG0		0x20B8
+#define ECCCLKALIGNREG1		0x20BC
+#define ECCCLKALIGNREG2		0x20C0
+
+/* CH0-CMD */
+#define CMDOBSCKEBBCTL		0x4800
+#define CMDDLLTXCTL		0x4808
+#define CMDDLLRXCTL		0x480C
+#define CMDMDLLCTL		0x4810
+#define CMDRCOMPODT		0x4814
+#define CMDDLLPICODER0		0x4820
+#define CMDDLLPICODER1		0x4824
+#define CMDCFGREG0		0x4840
+#define CMDPTRREG		0x4844
+#define CMDCLKALIGNREG0		0x4850
+#define CMDCLKALIGNREG1		0x4854
+#define CMDCLKALIGNREG2		0x4858
+#define CMDPMCONFIG0		0x485C
+#define CMDPMDLYREG0		0x4860
+#define CMDPMDLYREG1		0x4864
+#define CMDPMDLYREG2		0x4868
+#define CMDPMDLYREG3		0x486C
+#define CMDPMDLYREG4		0x4870
+#define CMDCLKALIGNSTS0		0x4874
+#define CMDCLKALIGNSTS1		0x4878
+#define CMDPMSTS0		0x487C
+#define CMDPMSTS1		0x4880
+#define CMDCOMPSLV		0x4884
+#define CMDBONUS0		0x488C
+#define CMDBONUS1		0x4890
+#define CMDVISALANECR0		0x4894
+#define CMDVISALANECR1		0x4898
+#define CMDVISACONTROLCR	0x489C
+#define CMDCLKGATE		0x48A0
+#define CMDTIMINGCTRL		0x48A4
+
+/* CH0-CLK-CTL */
+#define CCOBSCKEBBCTL		0x5800
+#define CCRCOMPIO		0x5804
+#define CCDLLTXCTL		0x5808
+#define CCDLLRXCTL		0x580C
+#define CCMDLLCTL		0x5810
+#define CCRCOMPODT		0x5814
+#define CCDLLPICODER0		0x5820
+#define CCDLLPICODER1		0x5824
+#define CCDDR3RESETCTL		0x5830
+#define CCCFGREG0		0x5838
+#define CCCFGREG1		0x5840
+#define CCPTRREG		0x5844
+#define CCCLKALIGNREG0		0x5850
+#define CCCLKALIGNREG1		0x5854
+#define CCCLKALIGNREG2		0x5858
+#define CCPMCONFIG0		0x585C
+#define CCPMDLYREG0		0x5860
+#define CCPMDLYREG1		0x5864
+#define CCPMDLYREG2		0x5868
+#define CCPMDLYREG3		0x586C
+#define CCPMDLYREG4		0x5870
+#define CCCLKALIGNSTS0		0x5874
+#define CCCLKALIGNSTS1		0x5878
+#define CCPMSTS0		0x587C
+#define CCPMSTS1		0x5880
+#define CCCOMPSLV1		0x5884
+#define CCCOMPSLV2		0x5888
+#define CCCOMPSLV3		0x588C
+#define CCBONUS0		0x5894
+#define CCBONUS1		0x5898
+#define CCVISALANECR0		0x589C
+#define CCVISALANECR1		0x58A0
+#define CCVISACONTROLCR		0x58A4
+#define CCCLKGATE		0x58A8
+#define CCTIMINGCTL		0x58AC
+
+/* COMP */
+#define CMPCTRL			0x6800
+#define SOFTRSTCNTL		0x6804
+#define MSCNTR			0x6808
+#define NMSCNTRL		0x680C
+#define LATCH1CTL		0x6814
+#define COMPVISALANECR0		0x681C
+#define COMPVISALANECR1		0x6820
+#define COMPVISACONTROLCR	0x6824
+#define COMPBONUS0		0x6830
+#define TCOCNTCTRL		0x683C
+#define DQANAODTPUCTL		0x6840
+#define DQANAODTPDCTL		0x6844
+#define DQANADRVPUCTL		0x6848
+#define DQANADRVPDCTL		0x684C
+#define DQANADLYPUCTL		0x6850
+#define DQANADLYPDCTL		0x6854
+#define DQANATCOPUCTL		0x6858
+#define DQANATCOPDCTL		0x685C
+#define CMDANADRVPUCTL		0x6868
+#define CMDANADRVPDCTL		0x686C
+#define CMDANADLYPUCTL		0x6870
+#define CMDANADLYPDCTL		0x6874
+#define CLKANAODTPUCTL		0x6880
+#define CLKANAODTPDCTL		0x6884
+#define CLKANADRVPUCTL		0x6888
+#define CLKANADRVPDCTL		0x688C
+#define CLKANADLYPUCTL		0x6890
+#define CLKANADLYPDCTL		0x6894
+#define CLKANATCOPUCTL		0x6898
+#define CLKANATCOPDCTL		0x689C
+#define DQSANAODTPUCTL		0x68A0
+#define DQSANAODTPDCTL		0x68A4
+#define DQSANADRVPUCTL		0x68A8
+#define DQSANADRVPDCTL		0x68AC
+#define DQSANADLYPUCTL		0x68B0
+#define DQSANADLYPDCTL		0x68B4
+#define DQSANATCOPUCTL		0x68B8
+#define DQSANATCOPDCTL		0x68BC
+#define CTLANADRVPUCTL		0x68C8
+#define CTLANADRVPDCTL		0x68CC
+#define CTLANADLYPUCTL		0x68D0
+#define CTLANADLYPDCTL		0x68D4
+#define CHNLBUFSTATIC		0x68F0
+#define COMPOBSCNTRL		0x68F4
+#define COMPBUFFDBG0		0x68F8
+#define COMPBUFFDBG1		0x68FC
+#define CFGMISCCH0		0x6900
+#define COMPEN0CH0		0x6904
+#define COMPEN1CH0		0x6908
+#define COMPEN2CH0		0x690C
+#define STATLEGEN0CH0		0x6910
+#define STATLEGEN1CH0		0x6914
+#define DQVREFCH0		0x6918
+#define CMDVREFCH0		0x691C
+#define CLKVREFCH0		0x6920
+#define DQSVREFCH0		0x6924
+#define CTLVREFCH0		0x6928
+#define TCOVREFCH0		0x692C
+#define DLYSELCH0		0x6930
+#define TCODRAMBUFODTCH0	0x6934
+#define CCBUFODTCH0		0x6938
+#define RXOFFSETCH0		0x693C
+#define DQODTPUCTLCH0		0x6940
+#define DQODTPDCTLCH0		0x6944
+#define DQDRVPUCTLCH0		0x6948
+#define DQDRVPDCTLCH0		0x694C
+#define DQDLYPUCTLCH0		0x6950
+#define DQDLYPDCTLCH0		0x6954
+#define DQTCOPUCTLCH0		0x6958
+#define DQTCOPDCTLCH0		0x695C
+#define CMDDRVPUCTLCH0		0x6968
+#define CMDDRVPDCTLCH0		0x696C
+#define CMDDLYPUCTLCH0		0x6970
+#define CMDDLYPDCTLCH0		0x6974
+#define CLKODTPUCTLCH0		0x6980
+#define CLKODTPDCTLCH0		0x6984
+#define CLKDRVPUCTLCH0		0x6988
+#define CLKDRVPDCTLCH0		0x698C
+#define CLKDLYPUCTLCH0		0x6990
+#define CLKDLYPDCTLCH0		0x6994
+#define CLKTCOPUCTLCH0		0x6998
+#define CLKTCOPDCTLCH0		0x699C
+#define DQSODTPUCTLCH0		0x69A0
+#define DQSODTPDCTLCH0		0x69A4
+#define DQSDRVPUCTLCH0		0x69A8
+#define DQSDRVPDCTLCH0		0x69AC
+#define DQSDLYPUCTLCH0		0x69B0
+#define DQSDLYPDCTLCH0		0x69B4
+#define DQSTCOPUCTLCH0		0x69B8
+#define DQSTCOPDCTLCH0		0x69BC
+#define CTLDRVPUCTLCH0		0x69C8
+#define CTLDRVPDCTLCH0		0x69CC
+#define CTLDLYPUCTLCH0		0x69D0
+#define CTLDLYPDCTLCH0		0x69D4
+#define FNLUPDTCTLCH0		0x69F0
+
+/* PLL */
+#define MPLLCTRL0		0x7800
+#define MPLLCTRL1		0x7808
+#define MPLLCSR0		0x7810
+#define MPLLCSR1		0x7814
+#define MPLLCSR2		0x7820
+#define MPLLDFT			0x7828
+#define MPLLMON0CTL		0x7830
+#define MPLLMON1CTL		0x7838
+#define MPLLMON2CTL		0x783C
+#define SFRTRIM			0x7850
+#define MPLLDFTOUT0		0x7858
+#define MPLLDFTOUT1		0x785C
+#define MASTERRSTN		0x7880
+#define PLLLOCKDEL		0x7884
+#define SFRDEL			0x7888
+#define CRUVISALANECR0		0x78F0
+#define CRUVISALANECR1		0x78F4
+#define CRUVISACONTROLCR	0x78F8
+#define IOSFVISALANECR0		0x78FC
+#define IOSFVISALANECR1		0x7900
+#define IOSFVISACONTROLCR	0x7904
+
+/* END DDRIO Registers */
+
+/* DRAM Specific Message Bus OpCodes */
+#define MSG_OP_DRAM_INIT	0x68
+#define MSG_OP_DRAM_WAKE	0xCA
+
+#define SAMPLE_SIZE		6
+
+/* must be less than this number to enable early deadband */
+#define EARLY_DB		0x12
+/* must be greater than this number to enable late deadband */
+#define LATE_DB			0x34
+
+#define CHX_REGS		(11 * 4)
+#define FULL_CLK		128
+#define HALF_CLK		64
+#define QRTR_CLK		32
+
+#define MCEIL(num, den)		((uint8_t)((num + den - 1) / den))
+#define MMAX(a, b)		((a) > (b) ? (a) : (b))
+#define DEAD_LOOP()		for (;;);
+
+#define MIN_RDQS_EYE		10	/* in PI Codes */
+#define MIN_VREF_EYE		10	/* in VREF Codes */
+/* how many RDQS codes to jump while margining */
+#define RDQS_STEP		1
+/* how many VREF codes to jump while margining */
+#define VREF_STEP		1
+/* offset into "vref_codes[]" for minimum allowed VREF setting */
+#define VREF_MIN		0x00
+/* offset into "vref_codes[]" for maximum allowed VREF setting */
+#define VREF_MAX		0x3F
+#define RDQS_MIN		0x00	/* minimum RDQS delay value */
+#define RDQS_MAX		0x3F	/* maximum RDQS delay value */
+
+/* how many WDQ codes to jump while margining */
+#define WDQ_STEP		1
+
+enum {
+	B,	/* BOTTOM VREF */
+	T	/* TOP VREF */
+};
+
+enum {
+	L,	/* LEFT RDQS */
+	R	/* RIGHT RDQS */
+};
+
+/* Memory Options */
+
+/* enable STATIC timing settings for RCVN (BACKUP_MODE) */
+#undef BACKUP_RCVN
+/* enable STATIC timing settings for WDQS (BACKUP_MODE) */
+#undef BACKUP_WDQS
+/* enable STATIC timing settings for RDQS (BACKUP_MODE) */
+#undef BACKUP_RDQS
+/* enable STATIC timing settings for WDQ (BACKUP_MODE) */
+#undef BACKUP_WDQ
+/* enable *COMP overrides (BACKUP_MODE) */
+#undef BACKUP_COMPS
+/* enable the RD_TRAIN eye check */
+#undef RX_EYE_CHECK
+
+/* enable Host to Memory Clock Alignment */
+#define HMC_TEST
+/* enable multi-rank support via rank2rank sharing */
+#define R2R_SHARING
+/* disable signals not used in 16bit mode of DDRIO */
+#define FORCE_16BIT_DDRIO
+
+#define PLATFORM_ID		1
+
+void clear_self_refresh(struct mrc_params *mrc_params);
+void prog_ddr_timing_control(struct mrc_params *mrc_params);
+void prog_decode_before_jedec(struct mrc_params *mrc_params);
+void perform_ddr_reset(struct mrc_params *mrc_params);
+void ddrphy_init(struct mrc_params *mrc_params);
+void perform_jedec_init(struct mrc_params *mrc_params);
+void set_ddr_init_complete(struct mrc_params *mrc_params);
+void restore_timings(struct mrc_params *mrc_params);
+void default_timings(struct mrc_params *mrc_params);
+void rcvn_cal(struct mrc_params *mrc_params);
+void wr_level(struct mrc_params *mrc_params);
+void prog_page_ctrl(struct mrc_params *mrc_params);
+void rd_train(struct mrc_params *mrc_params);
+void wr_train(struct mrc_params *mrc_params);
+void store_timings(struct mrc_params *mrc_params);
+void enable_scrambling(struct mrc_params *mrc_params);
+void prog_ddr_control(struct mrc_params *mrc_params);
+void prog_dra_drb(struct mrc_params *mrc_params);
+void perform_wake(struct mrc_params *mrc_params);
+void change_refresh_period(struct mrc_params *mrc_params);
+void set_auto_refresh(struct mrc_params *mrc_params);
+void ecc_enable(struct mrc_params *mrc_params);
+void memory_test(struct mrc_params *mrc_params);
+void lock_registers(struct mrc_params *mrc_params);
+
+#endif /* _SMC_H_ */
diff --git a/arch/x86/cpu/queensbay/Kconfig b/arch/x86/cpu/queensbay/Kconfig
index f6b52010c3..397e599f93 100644
--- a/arch/x86/cpu/queensbay/Kconfig
+++ b/arch/x86/cpu/queensbay/Kconfig
@@ -11,44 +11,6 @@ config INTEL_QUEENSBAY
 
 if INTEL_QUEENSBAY
 
-config HAVE_FSP
-	bool "Add an Firmware Support Package binary"
-	help
-	  Select this option to add an Firmware Support Package binary to
-	  the resulting U-Boot image. It is a binary blob which U-Boot uses
-	  to set up SDRAM and other chipset specific initialization.
-
-	  Note: Without this binary U-Boot will not be able to set up its
-	  SDRAM so will not boot.
-
-config FSP_FILE
-	string "Firmware Support Package binary filename"
-	depends on HAVE_FSP
-	default "fsp.bin"
-	help
-	  The filename of the file to use as Firmware Support Package binary
-	  in the board directory.
-
-config FSP_ADDR
-	hex "Firmware Support Package binary location"
-	depends on HAVE_FSP
-	default 0xfffc0000
-	help
-	  FSP is not Position Independent Code (PIC) and the whole FSP has to
-	  be rebased if it is placed at a location which is different from the
-	  perferred base address specified during the FSP build. Use Intel's
-	  Binary Configuration Tool (BCT) to do the rebase.
-
-	  The default base address of 0xfffc0000 indicates that the binary must
-	  be located at offset 0xc0000 from the beginning of a 1MB flash device.
-
-config FSP_TEMP_RAM_ADDR
-	hex
-	default 0x2000000
-	help
-	  Stack top address which is used in FspInit after DRAM is ready and
-	  CAR is disabled.
-
 config HAVE_CMC
 	bool "Add a Chipset Micro Code state machine binary"
 	help
diff --git a/arch/x86/cpu/queensbay/Makefile b/arch/x86/cpu/queensbay/Makefile
index 2c2ec01ed2..d8761fdfbd 100644
--- a/arch/x86/cpu/queensbay/Makefile
+++ b/arch/x86/cpu/queensbay/Makefile
@@ -4,6 +4,6 @@
 # SPDX-License-Identifier:	GPL-2.0+
 #
 
-obj-y += tnc_car.o tnc_dram.o tnc.o topcliff.o
-obj-y += fsp_configs.o fsp_support.o
+obj-y += fsp_configs.o
+obj-y += tnc.o topcliff.o
 obj-$(CONFIG_PCI) += tnc_pci.o
diff --git a/arch/x86/cpu/queensbay/fsp_configs.c b/arch/x86/cpu/queensbay/fsp_configs.c
index af28e457f6..78bc966bbd 100644
--- a/arch/x86/cpu/queensbay/fsp_configs.c
+++ b/arch/x86/cpu/queensbay/fsp_configs.c
@@ -6,7 +6,7 @@
  */
 
 #include <common.h>
-#include <asm/arch/fsp/fsp_support.h>
+#include <asm/fsp/fsp_support.h>
 
 void update_fsp_upd(struct upd_region *fsp_upd)
 {
diff --git a/arch/x86/cpu/queensbay/fsp_support.c b/arch/x86/cpu/queensbay/fsp_support.c
deleted file mode 100644
index aed3e2b300..0000000000
--- a/arch/x86/cpu/queensbay/fsp_support.c
+++ /dev/null
@@ -1,408 +0,0 @@
-/*
- * Copyright (C) 2013, Intel Corporation
- * Copyright (C) 2014, Bin Meng <bmeng.cn@gmail.com>
- *
- * SPDX-License-Identifier:	Intel
- */
-
-#include <common.h>
-#include <asm/arch/fsp/fsp_support.h>
-#include <asm/post.h>
-
-/**
- * Compares two GUIDs
- *
- * If the GUIDs are identical then true is returned.
- * If there are any bit differences in the two GUIDs, then false is returned.
- *
- * @guid1:        A pointer to a 128 bit GUID.
- * @guid2:        A pointer to a 128 bit GUID.
- *
- * @retval true:  guid1 and guid2 are identical.
- * @retval false: guid1 and guid2 are not identical.
- */
-static bool compare_guid(const struct efi_guid *guid1,
-			 const struct efi_guid *guid2)
-{
-	if (memcmp(guid1, guid2, sizeof(struct efi_guid)) == 0)
-		return true;
-	else
-		return false;
-}
-
-u32 __attribute__((optimize("O0"))) find_fsp_header(void)
-{
-	/*
-	 * This function may be called before the a stack is established,
-	 * so special care must be taken. First, it cannot declare any local
-	 * variable using stack. Only register variable can be used here.
-	 * Secondly, some compiler version will add prolog or epilog code
-	 * for the C function. If so the function call may not work before
-	 * stack is ready.
-	 *
-	 * GCC 4.8.1 has been verified to be working for the following codes.
-	 */
-	volatile register u8 *fsp asm("eax");
-
-	/* Initalize the FSP base */
-	fsp = (u8 *)CONFIG_FSP_ADDR;
-
-	/* Check the FV signature, _FVH */
-	if (((struct fv_header *)fsp)->sign == EFI_FVH_SIGNATURE) {
-		/* Go to the end of the FV header and align the address */
-		fsp += ((struct fv_header *)fsp)->ext_hdr_off;
-		fsp += ((struct fv_ext_header *)fsp)->ext_hdr_size;
-		fsp  = (u8 *)(((u32)fsp + 7) & 0xFFFFFFF8);
-	} else {
-		fsp  = 0;
-	}
-
-	/* Check the FFS GUID */
-	if (fsp &&
-	    ((struct ffs_file_header *)fsp)->name.data1 == FSP_GUID_DATA1 &&
-	    ((struct ffs_file_header *)fsp)->name.data2 == FSP_GUID_DATA2 &&
-	    ((struct ffs_file_header *)fsp)->name.data3 == FSP_GUID_DATA3 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[0] == FSP_GUID_DATA4_0 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[1] == FSP_GUID_DATA4_1 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[2] == FSP_GUID_DATA4_2 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[3] == FSP_GUID_DATA4_3 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[4] == FSP_GUID_DATA4_4 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[5] == FSP_GUID_DATA4_5 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[6] == FSP_GUID_DATA4_6 &&
-	    ((struct ffs_file_header *)fsp)->name.data4[7] == FSP_GUID_DATA4_7) {
-		/* Add the FFS header size to find the raw section header */
-		fsp += sizeof(struct ffs_file_header);
-	} else {
-		fsp = 0;
-	}
-
-	if (fsp &&
-	    ((struct raw_section *)fsp)->type == EFI_SECTION_RAW) {
-		/* Add the raw section header size to find the FSP header */
-		fsp += sizeof(struct raw_section);
-	} else {
-		fsp = 0;
-	}
-
-	return (u32)fsp;
-}
-
-void fsp_continue(struct shared_data *shared_data, u32 status, void *hob_list)
-{
-	u32 stack_len;
-	u32 stack_base;
-	u32 stack_top;
-
-	post_code(POST_MRC);
-
-	assert(status == 0);
-
-	/* Get the migrated stack in normal memory */
-	stack_base = (u32)fsp_get_bootloader_tmp_mem(hob_list, &stack_len);
-	assert(stack_base != 0);
-	stack_top  = stack_base + stack_len - sizeof(u32);
-
-	/*
-	 * Old stack base is stored at the very end of the stack top,
-	 * use it to calculate the migrated shared data base
-	 */
-	shared_data = (struct shared_data *)(stack_base +
-			((u32)shared_data - *(u32 *)stack_top));
-
-	/* The boot loader main function entry */
-	fsp_init_done(hob_list);
-}
-
-void fsp_init(u32 stack_top, u32 boot_mode, void *nvs_buf)
-{
-	struct shared_data shared_data;
-	fsp_init_f init;
-	struct fsp_init_params params;
-	struct fspinit_rtbuf rt_buf;
-	struct vpd_region *fsp_vpd;
-	struct fsp_header *fsp_hdr;
-	struct fsp_init_params *params_ptr;
-	struct upd_region *fsp_upd;
-
-	fsp_hdr = (struct fsp_header *)find_fsp_header();
-	if (fsp_hdr == NULL) {
-		/* No valid FSP info header was found */
-		panic("Invalid FSP header");
-	}
-
-	fsp_upd = (struct upd_region *)&shared_data.fsp_upd;
-	memset(&rt_buf, 0, sizeof(struct fspinit_rtbuf));
-
-	/* Reserve a gap in stack top */
-	rt_buf.common.stack_top = (u32 *)stack_top - 32;
-	rt_buf.common.boot_mode = boot_mode;
-	rt_buf.common.upd_data = (struct upd_region *)fsp_upd;
-
-	/* Get VPD region start */
-	fsp_vpd = (struct vpd_region *)(fsp_hdr->img_base +
-			fsp_hdr->cfg_region_off);
-
-	/* Verifify the VPD data region is valid */
-	assert((fsp_vpd->img_rev == VPD_IMAGE_REV) &&
-	       (fsp_vpd->sign == VPD_IMAGE_ID));
-
-	/* Copy default data from Flash */
-	memcpy(fsp_upd, (void *)(fsp_hdr->img_base + fsp_vpd->upd_offset),
-	       sizeof(struct upd_region));
-
-	/* Verifify the UPD data region is valid */
-	assert(fsp_upd->terminator == UPD_TERMINATOR);
-
-	/* Override any UPD setting if required */
-	update_fsp_upd(fsp_upd);
-
-	memset(&params, 0, sizeof(struct fsp_init_params));
-	params.nvs_buf = nvs_buf;
-	params.rt_buf = (struct fspinit_rtbuf *)&rt_buf;
-	params.continuation = (fsp_continuation_f)asm_continuation;
-
-	init = (fsp_init_f)(fsp_hdr->img_base + fsp_hdr->fsp_init);
-	params_ptr = &params;
-
-	shared_data.fsp_hdr = fsp_hdr;
-	shared_data.stack_top = (u32 *)stack_top;
-
-	post_code(POST_PRE_MRC);
-
-	/*
-	 * Use ASM code to ensure the register value in EAX & ECX
-	 * will be passed into BlContinuationFunc
-	 */
-	asm volatile (
-		"pushl	%0;"
-		"call	*%%eax;"
-		".global asm_continuation;"
-		"asm_continuation:;"
-		"movl	%%ebx, %%eax;"		/* shared_data */
-		"movl	4(%%esp), %%edx;"	/* status */
-		"movl	8(%%esp), %%ecx;"	/* hob_list */
-		"jmp	fsp_continue;"
-		: : "m"(params_ptr), "a"(init), "b"(&shared_data)
-	);
-
-	/*
-	 * Should never get here.
-	 * Control will continue from fsp_continue.
-	 * This line below is to prevent the compiler from optimizing
-	 * structure intialization.
-	 *
-	 * DO NOT REMOVE!
-	 */
-	init(&params);
-}
-
-u32 fsp_notify(struct fsp_header *fsp_hdr, u32 phase)
-{
-	fsp_notify_f notify;
-	struct fsp_notify_params params;
-	struct fsp_notify_params *params_ptr;
-	u32 status;
-
-	if (!fsp_hdr)
-		fsp_hdr = (struct fsp_header *)find_fsp_header();
-
-	if (fsp_hdr == NULL) {
-		/* No valid FSP info header */
-		panic("Invalid FSP header");
-	}
-
-	notify = (fsp_notify_f)(fsp_hdr->img_base + fsp_hdr->fsp_notify);
-	params.phase = phase;
-	params_ptr = &params;
-
-	/*
-	 * Use ASM code to ensure correct parameter is on the stack for
-	 * FspNotify as U-Boot is using different ABI from FSP
-	 */
-	asm volatile (
-		"pushl	%1;"		/* push notify phase */
-		"call	*%%eax;"	/* call FspNotify */
-		"addl	$4, %%esp;"	/* clean up the stack */
-		: "=a"(status) : "m"(params_ptr), "a"(notify), "m"(*params_ptr)
-	);
-
-	return status;
-}
-
-u32 fsp_get_usable_lowmem_top(const void *hob_list)
-{
-	const struct hob_header *hdr;
-	struct hob_res_desc *res_desc;
-	phys_addr_t phys_start;
-	u32 top;
-
-	/* Get the HOB list for processing */
-	hdr = hob_list;
-
-	/* * Collect memory ranges */
-	top = FSP_LOWMEM_BASE;
-	while (!end_of_hob(hdr)) {
-		if (hdr->type == HOB_TYPE_RES_DESC) {
-			res_desc = (struct hob_res_desc *)hdr;
-			if (res_desc->type == RES_SYS_MEM) {
-				phys_start = res_desc->phys_start;
-				/* Need memory above 1MB to be collected here */
-				if (phys_start >= FSP_LOWMEM_BASE &&
-				    phys_start < (phys_addr_t)FSP_HIGHMEM_BASE)
-					top += (u32)(res_desc->len);
-			}
-		}
-		hdr = get_next_hob(hdr);
-	}
-
-	return top;
-}
-
-u64 fsp_get_usable_highmem_top(const void *hob_list)
-{
-	const struct hob_header *hdr;
-	struct hob_res_desc *res_desc;
-	phys_addr_t phys_start;
-	u64 top;
-
-	/* Get the HOB list for processing */
-	hdr = hob_list;
-
-	/* Collect memory ranges */
-	top = FSP_HIGHMEM_BASE;
-	while (!end_of_hob(hdr)) {
-		if (hdr->type == HOB_TYPE_RES_DESC) {
-			res_desc = (struct hob_res_desc *)hdr;
-			if (res_desc->type == RES_SYS_MEM) {
-				phys_start = res_desc->phys_start;
-				/* Need memory above 1MB to be collected here */
-				if (phys_start >= (phys_addr_t)FSP_HIGHMEM_BASE)
-					top += (u32)(res_desc->len);
-			}
-		}
-		hdr = get_next_hob(hdr);
-	}
-
-	return top;
-}
-
-u64 fsp_get_reserved_mem_from_guid(const void *hob_list, u64 *len,
-				   struct efi_guid *guid)
-{
-	const struct hob_header *hdr;
-	struct hob_res_desc *res_desc;
-
-	/* Get the HOB list for processing */
-	hdr = hob_list;
-
-	/* Collect memory ranges */
-	while (!end_of_hob(hdr)) {
-		if (hdr->type == HOB_TYPE_RES_DESC) {
-			res_desc = (struct hob_res_desc *)hdr;
-			if (res_desc->type == RES_MEM_RESERVED) {
-				if (compare_guid(&res_desc->owner, guid)) {
-					if (len)
-						*len = (u32)(res_desc->len);
-
-					return (u64)(res_desc->phys_start);
-				}
-			}
-		}
-		hdr = get_next_hob(hdr);
-	}
-
-	return 0;
-}
-
-u32 fsp_get_fsp_reserved_mem(const void *hob_list, u32 *len)
-{
-	const struct efi_guid guid = FSP_HOB_RESOURCE_OWNER_FSP_GUID;
-	u64 length;
-	u32 base;
-
-	base = (u32)fsp_get_reserved_mem_from_guid(hob_list,
-			&length, (struct efi_guid *)&guid);
-	if ((len != 0) && (base != 0))
-		*len = (u32)length;
-
-	return base;
-}
-
-u32 fsp_get_tseg_reserved_mem(const void *hob_list, u32 *len)
-{
-	const struct efi_guid guid = FSP_HOB_RESOURCE_OWNER_TSEG_GUID;
-	u64 length;
-	u32 base;
-
-	base = (u32)fsp_get_reserved_mem_from_guid(hob_list,
-			&length, (struct efi_guid *)&guid);
-	if ((len != 0) && (base != 0))
-		*len = (u32)length;
-
-	return base;
-}
-
-const struct hob_header *fsp_get_next_hob(uint type, const void *hob_list)
-{
-	const struct hob_header *hdr;
-
-	hdr = hob_list;
-
-	/* Parse the HOB list until end of list or matching type is found */
-	while (!end_of_hob(hdr)) {
-		if (hdr->type == type)
-			return hdr;
-
-		hdr = get_next_hob(hdr);
-	}
-
-	return NULL;
-}
-
-const struct hob_header *fsp_get_next_guid_hob(const struct efi_guid *guid,
-					       const void *hob_list)
-{
-	const struct hob_header *hdr;
-	struct hob_guid *guid_hob;
-
-	hdr = hob_list;
-	while ((hdr = fsp_get_next_hob(HOB_TYPE_GUID_EXT,
-			hdr)) != NULL) {
-		guid_hob = (struct hob_guid *)hdr;
-		if (compare_guid(guid, &(guid_hob->name)))
-			break;
-		hdr = get_next_hob(hdr);
-	}
-
-	return hdr;
-}
-
-void *fsp_get_guid_hob_data(const void *hob_list, u32 *len,
-			    struct efi_guid *guid)
-{
-	const struct hob_header *guid_hob;
-
-	guid_hob = fsp_get_next_guid_hob(guid, hob_list);
-	if (guid_hob == NULL) {
-		return NULL;
-	} else {
-		if (len)
-			*len = get_guid_hob_data_size(guid_hob);
-
-		return get_guid_hob_data(guid_hob);
-	}
-}
-
-void *fsp_get_nvs_data(const void *hob_list, u32 *len)
-{
-	const struct efi_guid guid = FSP_NON_VOLATILE_STORAGE_HOB_GUID;
-
-	return fsp_get_guid_hob_data(hob_list, len, (struct efi_guid *)&guid);
-}
-
-void *fsp_get_bootloader_tmp_mem(const void *hob_list, u32 *len)
-{
-	const struct efi_guid guid = FSP_BOOTLOADER_TEMP_MEM_HOB_GUID;
-
-	return fsp_get_guid_hob_data(hob_list, len, (struct efi_guid *)&guid);
-}
diff --git a/arch/x86/cpu/queensbay/tnc.c b/arch/x86/cpu/queensbay/tnc.c
index 8637cdca2d..30ab725bb9 100644
--- a/arch/x86/cpu/queensbay/tnc.c
+++ b/arch/x86/cpu/queensbay/tnc.c
@@ -9,7 +9,7 @@
 #include <asm/pci.h>
 #include <asm/post.h>
 #include <asm/arch/tnc.h>
-#include <asm/arch/fsp/fsp_support.h>
+#include <asm/fsp/fsp_support.h>
 #include <asm/processor.h>
 
 static void unprotect_spi_flash(void)
@@ -43,30 +43,3 @@ int arch_cpu_init(void)
 
 	return 0;
 }
-
-int print_cpuinfo(void)
-{
-	post_code(POST_CPU_INFO);
-	return default_print_cpuinfo();
-}
-
-void reset_cpu(ulong addr)
-{
-	/* cold reset */
-	outb(0x06, PORT_RESET);
-}
-
-void board_final_cleanup(void)
-{
-	u32 status;
-
-	/* call into FspNotify */
-	debug("Calling into FSP (notify phase INIT_PHASE_BOOT): ");
-	status = fsp_notify(NULL, INIT_PHASE_BOOT);
-	if (status != FSP_SUCCESS)
-		debug("fail, error code %x\n", status);
-	else
-		debug("OK\n");
-
-	return;
-}
diff --git a/arch/x86/cpu/queensbay/tnc_car.S b/arch/x86/cpu/queensbay/tnc_car.S
deleted file mode 100644
index 5e09568b85..0000000000
--- a/arch/x86/cpu/queensbay/tnc_car.S
+++ /dev/null
@@ -1,124 +0,0 @@
-/*
- * Copyright (C) 2014, Bin Meng <bmeng.cn@gmail.com>
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-#include <config.h>
-#include <asm/post.h>
-
-.globl car_init
-car_init:
-	/*
-	 * Note: ebp holds the BIST value (built-in self test) so far, but ebp
-	 * will be destroyed through the FSP call, thus we have to test the
-	 * BIST value here before we call into FSP.
-	 */
-	test	%ebp, %ebp
-	jz	car_init_start
-	post_code(POST_BIST_FAILURE)
-	jmp	die
-
-car_init_start:
-	post_code(POST_CAR_START)
-	lea	find_fsp_header_romstack, %esp
-	jmp	find_fsp_header
-
-find_fsp_header_ret:
-	/* EAX points to FSP_INFO_HEADER */
-	mov	%eax, %ebp
-
-	/* sanity test */
-	cmp	$CONFIG_FSP_ADDR, %eax
-	jb	die
-
-	/* calculate TempRamInitEntry address */
-	mov	0x30(%ebp), %eax
-	add	0x1c(%ebp), %eax
-
-	/* call FSP TempRamInitEntry to setup temporary stack */
-	lea	temp_ram_init_romstack, %esp
-	jmp	*%eax
-
-temp_ram_init_ret:
-	addl	$4, %esp
-	cmp	$0, %eax
-	jnz	car_init_fail
-
-	post_code(POST_CAR_CPU_CACHE)
-
-	/*
-	 * The FSP TempRamInit initializes the ecx and edx registers to
-	 * point to a temporary but writable memory range (Cache-As-RAM).
-	 * ecx: the start of this temporary memory range,
-	 * edx: the end of this range.
-	 */
-
-	/* stack grows down from top of CAR */
-	movl	%edx, %esp
-
-	/*
-	 * TODO:
-	 *
-	 * According to FSP architecture spec, the fsp_init() will not return
-	 * to its caller, instead it requires the bootloader to provide a
-	 * so-called continuation function to pass into the FSP as a parameter
-	 * of fsp_init, and fsp_init() will call that continuation function
-	 * directly.
-	 *
-	 * The call to fsp_init() may need to be moved out of the car_init()
-	 * to cpu_init_f() with the help of some inline assembly codes.
-	 * Note there is another issue that fsp_init() will setup another stack
-	 * using the fsp_init parameter stack_top after DRAM is initialized,
-	 * which means any data on the previous stack (on the CAR) gets lost
-	 * (ie: U-Boot global_data). FSP is supposed to support such scenario,
-	 * however it does not work. This should be revisited in the future.
-	 */
-	movl	$CONFIG_FSP_TEMP_RAM_ADDR, %eax
-	xorl	%edx, %edx
-	xorl	%ecx, %ecx
-	call	fsp_init
-
-.global fsp_init_done
-fsp_init_done:
-	/*
-	 * We come here from FspInit with eax pointing to the HOB list.
-	 * Save eax to esi temporarily.
-	 */
-	movl	%eax, %esi
-	/*
-	 * Re-initialize the ebp (BIST) to zero, as we already reach here
-	 * which means we passed BIST testing before.
-	 */
-	xorl	%ebp, %ebp
-	jmp	car_init_ret
-
-car_init_fail:
-	post_code(POST_CAR_FAILURE)
-
-die:
-	hlt
-	jmp	die
-	hlt
-
-	/*
-	 * The function call before CAR initialization is tricky. It cannot
-	 * be called using the 'call' instruction but only the 'jmp' with
-	 * the help of a handcrafted stack in the ROM. The stack needs to
-	 * contain the function return address as well as the parameters.
-	 */
-	.balign	4
-find_fsp_header_romstack:
-	.long	find_fsp_header_ret
-
-	.balign	4
-temp_ram_init_romstack:
-	.long	temp_ram_init_ret
-	.long	temp_ram_init_params
-temp_ram_init_params:
-_dt_ucode_base_size:
-	/* These next two fields are filled in by ifdtool */
-	.long	0			/* microcode base */
-	.long	0			/* microcode size */
-	.long	CONFIG_SYS_MONITOR_BASE	/* code region base */
-	.long	CONFIG_SYS_MONITOR_LEN	/* code region size */
diff --git a/arch/x86/cpu/queensbay/tnc_dram.c b/arch/x86/cpu/queensbay/tnc_dram.c
deleted file mode 100644
index df79a39dd8..0000000000
--- a/arch/x86/cpu/queensbay/tnc_dram.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright (C) 2014, Bin Meng <bmeng.cn@gmail.com>
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-#include <common.h>
-#include <asm/arch/fsp/fsp_support.h>
-#include <asm/e820.h>
-#include <asm/post.h>
-
-DECLARE_GLOBAL_DATA_PTR;
-
-int dram_init(void)
-{
-	phys_size_t ram_size = 0;
-	const struct hob_header *hdr;
-	struct hob_res_desc *res_desc;
-
-	hdr = gd->arch.hob_list;
-	while (!end_of_hob(hdr)) {
-		if (hdr->type == HOB_TYPE_RES_DESC) {
-			res_desc = (struct hob_res_desc *)hdr;
-			if (res_desc->type == RES_SYS_MEM ||
-			    res_desc->type == RES_MEM_RESERVED) {
-				ram_size += res_desc->len;
-			}
-		}
-		hdr = get_next_hob(hdr);
-	}
-
-	gd->ram_size = ram_size;
-	post_code(POST_DRAM);
-
-	return 0;
-}
-
-void dram_init_banksize(void)
-{
-	gd->bd->bi_dram[0].start = 0;
-	gd->bd->bi_dram[0].size = gd->ram_size;
-}
-
-/*
- * This function looks for the highest region of memory lower than 4GB which
- * has enough space for U-Boot where U-Boot is aligned on a page boundary.
- * It overrides the default implementation found elsewhere which simply
- * picks the end of ram, wherever that may be. The location of the stack,
- * the relocation address, and how far U-Boot is moved by relocation are
- * set in the global data structure.
- */
-ulong board_get_usable_ram_top(ulong total_size)
-{
-	return fsp_get_usable_lowmem_top(gd->arch.hob_list);
-}
-
-unsigned install_e820_map(unsigned max_entries, struct e820entry *entries)
-{
-	unsigned num_entries = 0;
-	const struct hob_header *hdr;
-	struct hob_res_desc *res_desc;
-
-	hdr = gd->arch.hob_list;
-
-	while (!end_of_hob(hdr)) {
-		if (hdr->type == HOB_TYPE_RES_DESC) {
-			res_desc = (struct hob_res_desc *)hdr;
-			entries[num_entries].addr = res_desc->phys_start;
-			entries[num_entries].size = res_desc->len;
-
-			if (res_desc->type == RES_SYS_MEM)
-				entries[num_entries].type = E820_RAM;
-			else if (res_desc->type == RES_MEM_RESERVED)
-				entries[num_entries].type = E820_RESERVED;
-		}
-		hdr = get_next_hob(hdr);
-		num_entries++;
-	}
-
-	return num_entries;
-}
diff --git a/arch/x86/cpu/queensbay/tnc_pci.c b/arch/x86/cpu/queensbay/tnc_pci.c
index 39bff49c8d..6c291f9ee9 100644
--- a/arch/x86/cpu/queensbay/tnc_pci.c
+++ b/arch/x86/cpu/queensbay/tnc_pci.c
@@ -7,7 +7,7 @@
 #include <common.h>
 #include <pci.h>
 #include <asm/pci.h>
-#include <asm/arch/fsp/fsp_support.h>
+#include <asm/fsp/fsp_support.h>
 
 DECLARE_GLOBAL_DATA_PTR;
 
@@ -44,18 +44,3 @@ void board_pci_setup_hose(struct pci_controller *hose)
 
 	hose->region_count = 4;
 }
-
-int board_pci_post_scan(struct pci_controller *hose)
-{
-	u32 status;
-
-	/* call into FspNotify */
-	debug("Calling into FSP (notify phase INIT_PHASE_PCI): ");
-	status = fsp_notify(NULL, INIT_PHASE_PCI);
-	if (status != FSP_SUCCESS)
-		debug("fail, error code %x\n", status);
-	else
-		debug("OK\n");
-
-	return 0;
-}
diff --git a/arch/x86/cpu/queensbay/topcliff.c b/arch/x86/cpu/queensbay/topcliff.c
index b01422a965..9faf1b92bb 100644
--- a/arch/x86/cpu/queensbay/topcliff.c
+++ b/arch/x86/cpu/queensbay/topcliff.c
@@ -5,43 +5,16 @@
  */
 
 #include <common.h>
-#include <errno.h>
-#include <malloc.h>
-#include <pci.h>
+#include <mmc.h>
 #include <pci_ids.h>
-#include <sdhci.h>
 
 static struct pci_device_id mmc_supported[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TCF_SDIO_0 },
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TCF_SDIO_1 },
-	{ }
 };
 
 int cpu_mmc_init(bd_t *bis)
 {
-	struct sdhci_host *mmc_host;
-	pci_dev_t devbusfn;
-	u32 iobase;
-	int ret;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mmc_supported); i++) {
-		devbusfn =  pci_find_devices(mmc_supported, i);
-		if (devbusfn == -1)
-			return -ENODEV;
-
-		mmc_host = (struct sdhci_host *)malloc(sizeof(struct sdhci_host));
-		if (!mmc_host)
-			return -ENOMEM;
-
-		mmc_host->name = "Topcliff SDHCI";
-		pci_read_config_dword(devbusfn, PCI_BASE_ADDRESS_0, &iobase);
-		mmc_host->ioaddr = (void *)iobase;
-		mmc_host->quirks = 0;
-		ret = add_sdhci(mmc_host, 0, 0);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
+	return pci_mmc_init("Topcliff SDHCI", mmc_supported,
+			    ARRAY_SIZE(mmc_supported));
 }