driver/ddr/altera: Add the sdram calibration portion

This patch adds the DDR calibration portion of the Altera SDRAM driver.

Signed-off-by: Dinh Nguyen <dinguyen@opensource.altera.com>

drivers/ddr/altera/Makefile

@@ -0,0 +1,11 @@
+#
+# (C) Copyright 2000-2003
+# Wolfgang Denk, DENX Software Engineering, wd@denx.de.
+#
+# (C) Copyright 2010, Thomas Chou <thomas@wytron.com.tw>
+# Copyright (C) 2014 Altera Corporation <www.altera.com>
+#
+# SPDX-License-Identifier:	GPL-2.0+
+#
+
+obj-$(CONFIG_ALTERA_SDRAM) += sdram.o sequencer.o

drivers/ddr/altera/sequencer.c

@@ -0,0 +1,4051 @@
+/*
+ * Copyright Altera Corporation (C) 2012-2015
+ *
+ * SPDX-License-Identifier:    BSD-3-Clause
+ */
+
+#include <common.h>
+#include <asm/io.h>
+#include <asm/arch/sdram.h>
+#include "sequencer.h"
+#include "sequencer_auto.h"
+#include "sequencer_auto_ac_init.h"
+#include "sequencer_auto_inst_init.h"
+#include "sequencer_defines.h"
+
+static void scc_mgr_load_dqs_for_write_group(uint32_t write_group);
+
+static struct socfpga_sdr_rw_load_manager *sdr_rw_load_mgr_regs =
+	(struct socfpga_sdr_rw_load_manager *)(BASE_RW_MGR + 0x800);
+
+static struct socfpga_sdr_rw_load_jump_manager *sdr_rw_load_jump_mgr_regs =
+	(struct socfpga_sdr_rw_load_jump_manager *)(BASE_RW_MGR + 0xC00);
+
+static struct socfpga_sdr_reg_file *sdr_reg_file =
+	(struct socfpga_sdr_reg_file *)(BASE_REG_FILE);
+
+static struct socfpga_sdr_scc_mgr *sdr_scc_mgr =
+	(struct socfpga_sdr_scc_mgr *)(BASE_SCC_MGR + 0x0E00);
+
+static struct socfpga_phy_mgr_cmd *phy_mgr_cmd =
+	(struct socfpga_phy_mgr_cmd *)(BASE_PHY_MGR);
+
+static struct socfpga_phy_mgr_cfg *phy_mgr_cfg =
+	(struct socfpga_phy_mgr_cfg *)(BASE_PHY_MGR + 0x4000);
+
+static struct socfpga_data_mgr *data_mgr =
+	(struct socfpga_data_mgr *)(BASE_DATA_MGR);
+
+#define DELTA_D		1
+#define MGR_SELECT_MASK		0xf8000
+
+/*
+ * In order to reduce ROM size, most of the selectable calibration steps are
+ * decided at compile time based on the user's calibration mode selection,
+ * as captured by the STATIC_CALIB_STEPS selection below.
+ *
+ * However, to support simulation-time selection of fast simulation mode, where
+ * we skip everything except the bare minimum, we need a few of the steps to
+ * be dynamic.  In those cases, we either use the DYNAMIC_CALIB_STEPS for the
+ * check, which is based on the rtl-supplied value, or we dynamically compute
+ * the value to use based on the dynamically-chosen calibration mode
+ */
+
+#define DLEVEL 0
+#define STATIC_IN_RTL_SIM 0
+#define STATIC_SKIP_DELAY_LOOPS 0
+
+#define STATIC_CALIB_STEPS (STATIC_IN_RTL_SIM | CALIB_SKIP_FULL_TEST | \
+	STATIC_SKIP_DELAY_LOOPS)
+
+/* calibration steps requested by the rtl */
+uint16_t dyn_calib_steps;
+
+/*
+ * To make CALIB_SKIP_DELAY_LOOPS a dynamic conditional option
+ * instead of static, we use boolean logic to select between
+ * non-skip and skip values
+ *
+ * The mask is set to include all bits when not-skipping, but is
+ * zero when skipping
+ */
+
+uint16_t skip_delay_mask;	/* mask off bits when skipping/not-skipping */
+
+#define SKIP_DELAY_LOOP_VALUE_OR_ZERO(non_skip_value) \
+	((non_skip_value) & skip_delay_mask)
+
+struct gbl_type *gbl;
+struct param_type *param;
+uint32_t curr_shadow_reg;
+
+static uint32_t rw_mgr_mem_calibrate_write_test(uint32_t rank_bgn,
+	uint32_t write_group, uint32_t use_dm,
+	uint32_t all_correct, uint32_t *bit_chk, uint32_t all_ranks);
+
+static u32 sdr_get_addr(u32 *base)
+{
+	u32 addr = (u32)base & MGR_SELECT_MASK;
+
+	switch (addr) {
+	case BASE_PHY_MGR:
+		addr = (((u32)base >> 8) & (1 << 6)) | ((u32)base & 0x3f) |
+			SDR_PHYGRP_PHYMGRGRP_ADDRESS;
+		break;
+	case BASE_RW_MGR:
+		addr = ((u32)base & 0x1fff) | SDR_PHYGRP_RWMGRGRP_ADDRESS;
+		break;
+	case BASE_DATA_MGR:
+		addr = ((u32)base & 0x7ff) | SDR_PHYGRP_DATAMGRGRP_ADDRESS;
+		break;
+	case BASE_SCC_MGR:
+		addr = ((u32)base & 0xfff) | SDR_PHYGRP_SCCGRP_ADDRESS;
+		break;
+	case BASE_REG_FILE:
+		addr = ((u32)base & 0x7ff) | SDR_PHYGRP_REGFILEGRP_ADDRESS;
+		break;
+	case BASE_MMR:
+		addr = ((u32)base & 0xfff) | SDR_CTRLGRP_ADDRESS;
+		break;
+	default:
+		return -1;
+	}
+
+	return addr;
+}
+
+static void set_failing_group_stage(uint32_t group, uint32_t stage,
+	uint32_t substage)
+{
+	/*
+	 * Only set the global stage if there was not been any other
+	 * failing group
+	 */
+	if (gbl->error_stage == CAL_STAGE_NIL)	{
+		gbl->error_substage = substage;
+		gbl->error_stage = stage;
+		gbl->error_group = group;
+	}
+}
+
+static void reg_file_set_group(uint32_t set_group)
+{
+	u32 addr = sdr_get_addr(&sdr_reg_file->cur_stage);
+
+	/* Read the current group and stage */
+	uint32_t cur_stage_group = readl(SOCFPGA_SDR_ADDRESS + addr);
+
+	/* Clear the group */
+	cur_stage_group &= 0x0000FFFF;
+
+	/* Set the group */
+	cur_stage_group |= (set_group << 16);
+
+	/* Write the data back */
+	writel(cur_stage_group, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void reg_file_set_stage(uint32_t set_stage)
+{
+	u32 addr = sdr_get_addr(&sdr_reg_file->cur_stage);
+	/* Read the current group and stage */
+	uint32_t cur_stage_group = readl(SOCFPGA_SDR_ADDRESS + addr);
+
+	/* Clear the stage and substage */
+	cur_stage_group &= 0xFFFF0000;
+
+	/* Set the stage */
+	cur_stage_group |= (set_stage & 0x000000FF);
+
+	/* Write the data back */
+	writel(cur_stage_group, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void reg_file_set_sub_stage(uint32_t set_sub_stage)
+{
+	u32 addr = sdr_get_addr(&sdr_reg_file->cur_stage);
+	/* Read the current group and stage */
+	uint32_t cur_stage_group = readl(SOCFPGA_SDR_ADDRESS + addr);
+
+	/* Clear the substage */
+	cur_stage_group &= 0xFFFF00FF;
+
+	/* Set the sub stage */
+	cur_stage_group |= ((set_sub_stage << 8) & 0x0000FF00);
+
+	/* Write the data back */
+	writel(cur_stage_group, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void initialize(void)
+{
+	u32 addr = sdr_get_addr(&phy_mgr_cfg->mux_sel);
+
+	debug("%s:%d\n", __func__, __LINE__);
+	/* USER calibration has control over path to memory */
+	/*
+	 * In Hard PHY this is a 2-bit control:
+	 * 0: AFI Mux Select
+	 * 1: DDIO Mux Select
+	 */
+	writel(0x3, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* USER memory clock is not stable we begin initialization  */
+	addr = sdr_get_addr(&phy_mgr_cfg->reset_mem_stbl);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* USER calibration status all set to zero */
+	addr = sdr_get_addr(&phy_mgr_cfg->cal_status);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&phy_mgr_cfg->cal_debug_info);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	if ((dyn_calib_steps & CALIB_SKIP_ALL) != CALIB_SKIP_ALL) {
+		param->read_correct_mask_vg  = ((uint32_t)1 <<
+			(RW_MGR_MEM_DQ_PER_READ_DQS /
+			RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS)) - 1;
+		param->write_correct_mask_vg = ((uint32_t)1 <<
+			(RW_MGR_MEM_DQ_PER_READ_DQS /
+			RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS)) - 1;
+		param->read_correct_mask     = ((uint32_t)1 <<
+			RW_MGR_MEM_DQ_PER_READ_DQS) - 1;
+		param->write_correct_mask    = ((uint32_t)1 <<
+			RW_MGR_MEM_DQ_PER_WRITE_DQS) - 1;
+		param->dm_correct_mask       = ((uint32_t)1 <<
+			(RW_MGR_MEM_DATA_WIDTH / RW_MGR_MEM_DATA_MASK_WIDTH))
+			- 1;
+	}
+}
+
+static void set_rank_and_odt_mask(uint32_t rank, uint32_t odt_mode)
+{
+	uint32_t odt_mask_0 = 0;
+	uint32_t odt_mask_1 = 0;
+	uint32_t cs_and_odt_mask;
+	uint32_t addr;
+
+	if (odt_mode == RW_MGR_ODT_MODE_READ_WRITE) {
+		if (RW_MGR_MEM_NUMBER_OF_RANKS == 1) {
+			/*
+			 * 1 Rank
+			 * Read: ODT = 0
+			 * Write: ODT = 1
+			 */
+			odt_mask_0 = 0x0;
+			odt_mask_1 = 0x1;
+		} else if (RW_MGR_MEM_NUMBER_OF_RANKS == 2) {
+			/* 2 Ranks */
+			if (RW_MGR_MEM_NUMBER_OF_CS_PER_DIMM == 1) {
+				/* - Dual-Slot , Single-Rank
+				 * (1 chip-select per DIMM)
+				 * OR
+				 * - RDIMM, 4 total CS (2 CS per DIMM)
+				 * means 2 DIMM
+				 * Since MEM_NUMBER_OF_RANKS is 2 they are
+				 * both single rank
+				 * with 2 CS each (special for RDIMM)
+				 * Read: Turn on ODT on the opposite rank
+				 * Write: Turn on ODT on all ranks
+				 */
+				odt_mask_0 = 0x3 & ~(1 << rank);
+				odt_mask_1 = 0x3;
+			} else {
+				/*
+				 * USER - Single-Slot , Dual-rank DIMMs
+				 * (2 chip-selects per DIMM)
+				 * USER Read: Turn on ODT off on all ranks
+				 * USER Write: Turn on ODT on active rank
+				 */
+				odt_mask_0 = 0x0;
+				odt_mask_1 = 0x3 & (1 << rank);
+			}
+				} else {
+			/* 4 Ranks
+			 * Read:
+			 * ----------+-----------------------+
+			 *           |                       |
+			 *           |         ODT           |
+			 * Read From +-----------------------+
+			 *   Rank    |  3  |  2  |  1  |  0  |
+			 * ----------+-----+-----+-----+-----+
+			 *     0     |  0  |  1  |  0  |  0  |
+			 *     1     |  1  |  0  |  0  |  0  |
+			 *     2     |  0  |  0  |  0  |  1  |
+			 *     3     |  0  |  0  |  1  |  0  |
+			 * ----------+-----+-----+-----+-----+
+			 *
+			 * Write:
+			 * ----------+-----------------------+
+			 *           |                       |
+			 *           |         ODT           |
+			 * Write To  +-----------------------+
+			 *   Rank    |  3  |  2  |  1  |  0  |
+			 * ----------+-----+-----+-----+-----+
+			 *     0     |  0  |  1  |  0  |  1  |
+			 *     1     |  1  |  0  |  1  |  0  |
+			 *     2     |  0  |  1  |  0  |  1  |
+			 *     3     |  1  |  0  |  1  |  0  |
+			 * ----------+-----+-----+-----+-----+
+			 */
+			switch (rank) {
+			case 0:
+				odt_mask_0 = 0x4;
+				odt_mask_1 = 0x5;
+				break;
+			case 1:
+				odt_mask_0 = 0x8;
+				odt_mask_1 = 0xA;
+				break;
+			case 2:
+				odt_mask_0 = 0x1;
+				odt_mask_1 = 0x5;
+				break;
+			case 3:
+				odt_mask_0 = 0x2;
+				odt_mask_1 = 0xA;
+				break;
+			}
+		}
+	} else {
+		odt_mask_0 = 0x0;
+		odt_mask_1 = 0x0;
+	}
+
+	cs_and_odt_mask =
+		(0xFF & ~(1 << rank)) |
+		((0xFF & odt_mask_0) << 8) |
+		((0xFF & odt_mask_1) << 16);
+	addr = sdr_get_addr((u32 *)RW_MGR_SET_CS_AND_ODT_MASK);
+	writel(cs_and_odt_mask, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void scc_mgr_initialize(void)
+{
+	u32 addr = sdr_get_addr((u32 *)SCC_MGR_HHP_RFILE);
+
+	/*
+	 * Clear register file for HPS
+	 * 16 (2^4) is the size of the full register file in the scc mgr:
+	 *	RFILE_DEPTH = log2(MEM_DQ_PER_DQS + 1 + MEM_DM_PER_DQS +
+	 * MEM_IF_READ_DQS_WIDTH - 1) + 1;
+	 */
+	uint32_t i;
+	for (i = 0; i < 16; i++) {
+		debug_cond(DLEVEL == 1, "%s:%d: Clearing SCC RFILE index %u",
+			   __func__, __LINE__, i);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr + (i << 2));
+	}
+}
+
+static void scc_mgr_set_dqs_bus_in_delay(uint32_t read_group,
+						uint32_t delay)
+{
+	u32 addr = sdr_get_addr((u32 *)SCC_MGR_DQS_IN_DELAY);
+
+	/* Load the setting in the SCC manager */
+	writel(delay, SOCFPGA_SDR_ADDRESS + addr + (read_group << 2));
+}
+
+static void scc_mgr_set_dqs_io_in_delay(uint32_t write_group,
+	uint32_t delay)
+{
+	u32 addr = sdr_get_addr((u32 *)SCC_MGR_IO_IN_DELAY);
+
+	writel(delay, SOCFPGA_SDR_ADDRESS + addr + (RW_MGR_MEM_DQ_PER_WRITE_DQS << 2));
+}
+
+static void scc_mgr_set_dqs_en_phase(uint32_t read_group, uint32_t phase)
+{
+	u32 addr = sdr_get_addr((u32 *)SCC_MGR_DQS_EN_PHASE);
+
+	/* Load the setting in the SCC manager */
+	writel(phase, SOCFPGA_SDR_ADDRESS + addr + (read_group << 2));
+}
+
+static void scc_mgr_set_dqs_en_phase_all_ranks(uint32_t read_group,
+					       uint32_t phase)
+{
+	uint32_t r;
+	uint32_t update_scan_chains;
+	uint32_t addr;
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS;
+	     r += NUM_RANKS_PER_SHADOW_REG) {
+		/*
+		 * USER although the h/w doesn't support different phases per
+		 * shadow register, for simplicity our scc manager modeling
+		 * keeps different phase settings per shadow reg, and it's
+		 * important for us to keep them in sync to match h/w.
+		 * for efficiency, the scan chain update should occur only
+		 * once to sr0.
+		 */
+		update_scan_chains = (r == 0) ? 1 : 0;
+
+		scc_mgr_set_dqs_en_phase(read_group, phase);
+
+		if (update_scan_chains) {
+			addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+			writel(read_group, SOCFPGA_SDR_ADDRESS + addr);
+
+			addr = sdr_get_addr(&sdr_scc_mgr->update);
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+		}
+	}
+}
+
+static void scc_mgr_set_dqdqs_output_phase(uint32_t write_group,
+						  uint32_t phase)
+{
+	u32 addr = sdr_get_addr((u32 *)SCC_MGR_DQDQS_OUT_PHASE);
+
+	/* Load the setting in the SCC manager */
+	writel(phase, SOCFPGA_SDR_ADDRESS + addr + (write_group << 2));
+}
+
+static void scc_mgr_set_dqdqs_output_phase_all_ranks(uint32_t write_group,
+						     uint32_t phase)
+{
+	uint32_t r;
+	uint32_t update_scan_chains;
+	uint32_t addr;
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS;
+	     r += NUM_RANKS_PER_SHADOW_REG) {
+		/*
+		 * USER although the h/w doesn't support different phases per
+		 * shadow register, for simplicity our scc manager modeling
+		 * keeps different phase settings per shadow reg, and it's
+		 * important for us to keep them in sync to match h/w.
+		 * for efficiency, the scan chain update should occur only
+		 * once to sr0.
+		 */
+		update_scan_chains = (r == 0) ? 1 : 0;
+
+		scc_mgr_set_dqdqs_output_phase(write_group, phase);
+
+		if (update_scan_chains) {
+			addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+			writel(write_group, SOCFPGA_SDR_ADDRESS + addr);
+
+			addr = sdr_get_addr(&sdr_scc_mgr->update);
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+		}
+	}
+}
+
+static void scc_mgr_set_dqs_en_delay(uint32_t read_group, uint32_t delay)
+{
+	uint32_t addr = sdr_get_addr((u32 *)SCC_MGR_DQS_EN_DELAY);
+
+	/* Load the setting in the SCC manager */
+	writel(delay + IO_DQS_EN_DELAY_OFFSET, SOCFPGA_SDR_ADDRESS + addr +
+	       (read_group << 2));
+}
+
+static void scc_mgr_set_dqs_en_delay_all_ranks(uint32_t read_group,
+					       uint32_t delay)
+{
+	uint32_t r;
+	uint32_t addr;
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS;
+		r += NUM_RANKS_PER_SHADOW_REG) {
+		scc_mgr_set_dqs_en_delay(read_group, delay);
+
+		addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+		writel(read_group, SOCFPGA_SDR_ADDRESS + addr);
+		/*
+		 * In shadow register mode, the T11 settings are stored in
+		 * registers in the core, which are updated by the DQS_ENA
+		 * signals. Not issuing the SCC_MGR_UPD command allows us to
+		 * save lots of rank switching overhead, by calling
+		 * select_shadow_regs_for_update with update_scan_chains
+		 * set to 0.
+		 */
+		addr = sdr_get_addr(&sdr_scc_mgr->update);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	}
+	/*
+	 * In shadow register mode, the T11 settings are stored in
+	 * registers in the core, which are updated by the DQS_ENA
+	 * signals. Not issuing the SCC_MGR_UPD command allows us to
+	 * save lots of rank switching overhead, by calling
+	 * select_shadow_regs_for_update with update_scan_chains
+	 * set to 0.
+	 */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void scc_mgr_set_oct_out1_delay(uint32_t write_group, uint32_t delay)
+{
+	uint32_t read_group;
+	uint32_t addr = sdr_get_addr((u32 *)SCC_MGR_OCT_OUT1_DELAY);
+
+	/*
+	 * Load the setting in the SCC manager
+	 * Although OCT affects only write data, the OCT delay is controlled
+	 * by the DQS logic block which is instantiated once per read group.
+	 * For protocols where a write group consists of multiple read groups,
+	 * the setting must be set multiple times.
+	 */
+	for (read_group = write_group * RW_MGR_MEM_IF_READ_DQS_WIDTH /
+	     RW_MGR_MEM_IF_WRITE_DQS_WIDTH;
+	     read_group < (write_group + 1) * RW_MGR_MEM_IF_READ_DQS_WIDTH /
+	     RW_MGR_MEM_IF_WRITE_DQS_WIDTH; ++read_group)
+		writel(delay, SOCFPGA_SDR_ADDRESS + addr + (read_group << 2));
+}
+
+static void scc_mgr_set_dq_out1_delay(uint32_t write_group,
+				      uint32_t dq_in_group, uint32_t delay)
+{
+	uint32_t addr = sdr_get_addr((u32 *)SCC_MGR_IO_OUT1_DELAY);
+
+	/* Load the setting in the SCC manager */
+	writel(delay, SOCFPGA_SDR_ADDRESS + addr + (dq_in_group << 2));
+}
+
+static void scc_mgr_set_dq_in_delay(uint32_t write_group,
+	uint32_t dq_in_group, uint32_t delay)
+{
+	uint32_t addr = sdr_get_addr((u32 *)SCC_MGR_IO_IN_DELAY);
+
+	/* Load the setting in the SCC manager */
+	writel(delay, SOCFPGA_SDR_ADDRESS + addr + (dq_in_group << 2));
+}
+
+static void scc_mgr_set_hhp_extras(void)
+{
+	/*
+	 * Load the fixed setting in the SCC manager
+	 * bits: 0:0 = 1'b1   - dqs bypass
+	 * bits: 1:1 = 1'b1   - dq bypass
+	 * bits: 4:2 = 3'b001   - rfifo_mode
+	 * bits: 6:5 = 2'b01  - rfifo clock_select
+	 * bits: 7:7 = 1'b0  - separate gating from ungating setting
+	 * bits: 8:8 = 1'b0  - separate OE from Output delay setting
+	 */
+	uint32_t value = (0<<8) | (0<<7) | (1<<5) | (1<<2) | (1<<1) | (1<<0);
+	uint32_t addr = sdr_get_addr((u32 *)SCC_MGR_HHP_GLOBALS);
+
+	writel(value, SOCFPGA_SDR_ADDRESS + addr + SCC_MGR_HHP_EXTRAS_OFFSET);
+}
+
+static void scc_mgr_set_dqs_out1_delay(uint32_t write_group,
+					      uint32_t delay)
+{
+	uint32_t addr = sdr_get_addr((u32 *)SCC_MGR_IO_OUT1_DELAY);
+
+	/* Load the setting in the SCC manager */
+	writel(delay, SOCFPGA_SDR_ADDRESS + addr + (RW_MGR_MEM_DQ_PER_WRITE_DQS << 2));
+}
+
+static void scc_mgr_set_dm_out1_delay(uint32_t write_group,
+					     uint32_t dm, uint32_t delay)
+{
+	uint32_t addr = sdr_get_addr((u32 *)SCC_MGR_IO_OUT1_DELAY);
+
+	/* Load the setting in the SCC manager */
+	writel(delay, SOCFPGA_SDR_ADDRESS + addr +
+		((RW_MGR_MEM_DQ_PER_WRITE_DQS + 1 + dm) << 2));
+}
+
+/*
+ * USER Zero all DQS config
+ * TODO: maybe rename to scc_mgr_zero_dqs_config (or something)
+ */
+static void scc_mgr_zero_all(void)
+{
+	uint32_t i, r;
+	uint32_t addr;
+
+	/*
+	 * USER Zero all DQS config settings, across all groups and all
+	 * shadow registers
+	 */
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS; r +=
+	     NUM_RANKS_PER_SHADOW_REG) {
+		for (i = 0; i < RW_MGR_MEM_IF_READ_DQS_WIDTH; i++) {
+			/*
+			 * The phases actually don't exist on a per-rank basis,
+			 * but there's no harm updating them several times, so
+			 * let's keep the code simple.
+			 */
+			scc_mgr_set_dqs_bus_in_delay(i, IO_DQS_IN_RESERVE);
+			scc_mgr_set_dqs_en_phase(i, 0);
+			scc_mgr_set_dqs_en_delay(i, 0);
+		}
+
+		for (i = 0; i < RW_MGR_MEM_IF_WRITE_DQS_WIDTH; i++) {
+			scc_mgr_set_dqdqs_output_phase(i, 0);
+			/* av/cv don't have out2 */
+			scc_mgr_set_oct_out1_delay(i, IO_DQS_OUT_RESERVE);
+		}
+	}
+
+	/* multicast to all DQS group enables */
+	addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+	writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void scc_set_bypass_mode(uint32_t write_group, uint32_t mode)
+{
+	uint32_t addr;
+	/* mode = 0 : Do NOT bypass - Half Rate Mode */
+	/* mode = 1 : Bypass - Full Rate Mode */
+
+	/* only need to set once for all groups, pins, dq, dqs, dm */
+	if (write_group == 0) {
+		debug_cond(DLEVEL == 1, "%s:%d Setting HHP Extras\n", __func__,
+			   __LINE__);
+		scc_mgr_set_hhp_extras();
+		debug_cond(DLEVEL == 1, "%s:%d Done Setting HHP Extras\n",
+			  __func__, __LINE__);
+	}
+	/* multicast to all DQ enables */
+	addr = sdr_get_addr(&sdr_scc_mgr->dq_ena);
+	writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_scc_mgr->dm_ena);
+	writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* update current DQS IO enable */
+	addr = sdr_get_addr(&sdr_scc_mgr->dqs_io_ena);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* update the DQS logic */
+	addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+	writel(write_group, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* hit update */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void scc_mgr_zero_group(uint32_t write_group, uint32_t test_begin,
+			       int32_t out_only)
+{
+	uint32_t i, r;
+	uint32_t addr;
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS; r +=
+		NUM_RANKS_PER_SHADOW_REG) {
+		/* Zero all DQ config settings */
+		for (i = 0; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++) {
+			scc_mgr_set_dq_out1_delay(write_group, i, 0);
+			if (!out_only)
+				scc_mgr_set_dq_in_delay(write_group, i, 0);
+		}
+
+		/* multicast to all DQ enables */
+		addr = sdr_get_addr(&sdr_scc_mgr->dq_ena);
+		writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* Zero all DM config settings */
+		for (i = 0; i < RW_MGR_NUM_DM_PER_WRITE_GROUP; i++) {
+			scc_mgr_set_dm_out1_delay(write_group, i, 0);
+		}
+
+		/* multicast to all DM enables */
+		addr = sdr_get_addr(&sdr_scc_mgr->dm_ena);
+		writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* zero all DQS io settings */
+		if (!out_only)
+			scc_mgr_set_dqs_io_in_delay(write_group, 0);
+		/* av/cv don't have out2 */
+		scc_mgr_set_dqs_out1_delay(write_group, IO_DQS_OUT_RESERVE);
+		scc_mgr_set_oct_out1_delay(write_group, IO_DQS_OUT_RESERVE);
+		scc_mgr_load_dqs_for_write_group(write_group);
+
+		/* multicast to all DQS IO enables (only 1) */
+		addr = sdr_get_addr(&sdr_scc_mgr->dqs_io_ena);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* hit update to zero everything */
+		addr = sdr_get_addr(&sdr_scc_mgr->update);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	}
+}
+
+/* load up dqs config settings */
+static void scc_mgr_load_dqs(uint32_t dqs)
+{
+	uint32_t addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+
+	writel(dqs, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void scc_mgr_load_dqs_for_write_group(uint32_t write_group)
+{
+	uint32_t read_group;
+	uint32_t addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+	/*
+	 * Although OCT affects only write data, the OCT delay is controlled
+	 * by the DQS logic block which is instantiated once per read group.
+	 * For protocols where a write group consists of multiple read groups,
+	 * the setting must be scanned multiple times.
+	 */
+	for (read_group = write_group * RW_MGR_MEM_IF_READ_DQS_WIDTH /
+	     RW_MGR_MEM_IF_WRITE_DQS_WIDTH;
+	     read_group < (write_group + 1) * RW_MGR_MEM_IF_READ_DQS_WIDTH /
+	     RW_MGR_MEM_IF_WRITE_DQS_WIDTH; ++read_group)
+		writel(read_group, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+/* load up dqs io config settings */
+static void scc_mgr_load_dqs_io(void)
+{
+	uint32_t addr = sdr_get_addr(&sdr_scc_mgr->dqs_io_ena);
+
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+/* load up dq config settings */
+static void scc_mgr_load_dq(uint32_t dq_in_group)
+{
+	uint32_t addr = sdr_get_addr(&sdr_scc_mgr->dq_ena);
+
+	writel(dq_in_group, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+/* load up dm config settings */
+static void scc_mgr_load_dm(uint32_t dm)
+{
+	uint32_t addr = sdr_get_addr(&sdr_scc_mgr->dm_ena);
+
+	writel(dm, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+/*
+ * apply and load a particular input delay for the DQ pins in a group
+ * group_bgn is the index of the first dq pin (in the write group)
+ */
+static void scc_mgr_apply_group_dq_in_delay(uint32_t write_group,
+					    uint32_t group_bgn, uint32_t delay)
+{
+	uint32_t i, p;
+
+	for (i = 0, p = group_bgn; i < RW_MGR_MEM_DQ_PER_READ_DQS; i++, p++) {
+		scc_mgr_set_dq_in_delay(write_group, p, delay);
+		scc_mgr_load_dq(p);
+	}
+}
+
+/* apply and load a particular output delay for the DQ pins in a group */
+static void scc_mgr_apply_group_dq_out1_delay(uint32_t write_group,
+					      uint32_t group_bgn,
+					      uint32_t delay1)
+{
+	uint32_t i, p;
+
+	for (i = 0, p = group_bgn; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++, p++) {
+		scc_mgr_set_dq_out1_delay(write_group, i, delay1);
+		scc_mgr_load_dq(i);
+	}
+}
+
+/* apply and load a particular output delay for the DM pins in a group */
+static void scc_mgr_apply_group_dm_out1_delay(uint32_t write_group,
+					      uint32_t delay1)
+{
+	uint32_t i;
+
+	for (i = 0; i < RW_MGR_NUM_DM_PER_WRITE_GROUP; i++) {
+		scc_mgr_set_dm_out1_delay(write_group, i, delay1);
+		scc_mgr_load_dm(i);
+	}
+}
+
+
+/* apply and load delay on both DQS and OCT out1 */
+static void scc_mgr_apply_group_dqs_io_and_oct_out1(uint32_t write_group,
+						    uint32_t delay)
+{
+	scc_mgr_set_dqs_out1_delay(write_group, delay);
+	scc_mgr_load_dqs_io();
+
+	scc_mgr_set_oct_out1_delay(write_group, delay);
+	scc_mgr_load_dqs_for_write_group(write_group);
+}
+
+/* apply a delay to the entire output side: DQ, DM, DQS, OCT */
+static void scc_mgr_apply_group_all_out_delay_add(uint32_t write_group,
+						  uint32_t group_bgn,
+						  uint32_t delay)
+{
+	uint32_t i, p, new_delay;
+
+	/* dq shift */
+	for (i = 0, p = group_bgn; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++, p++) {
+		new_delay = READ_SCC_DQ_OUT2_DELAY;
+		new_delay += delay;
+
+		if (new_delay > IO_IO_OUT2_DELAY_MAX) {
+			debug_cond(DLEVEL == 1, "%s:%d (%u, %u, %u) DQ[%u,%u]:\
+				   %u > %lu => %lu", __func__, __LINE__,
+				   write_group, group_bgn, delay, i, p, new_delay,
+				   (long unsigned int)IO_IO_OUT2_DELAY_MAX,
+				   (long unsigned int)IO_IO_OUT2_DELAY_MAX);
+			new_delay = IO_IO_OUT2_DELAY_MAX;
+		}
+
+		scc_mgr_load_dq(i);
+	}
+
+	/* dm shift */
+	for (i = 0; i < RW_MGR_NUM_DM_PER_WRITE_GROUP; i++) {
+		new_delay = READ_SCC_DM_IO_OUT2_DELAY;
+		new_delay += delay;
+
+		if (new_delay > IO_IO_OUT2_DELAY_MAX) {
+			debug_cond(DLEVEL == 1, "%s:%d (%u, %u, %u) DM[%u]:\
+				   %u > %lu => %lu\n",  __func__, __LINE__,
+				   write_group, group_bgn, delay, i, new_delay,
+				   (long unsigned int)IO_IO_OUT2_DELAY_MAX,
+				   (long unsigned int)IO_IO_OUT2_DELAY_MAX);
+			new_delay = IO_IO_OUT2_DELAY_MAX;
+		}
+
+		scc_mgr_load_dm(i);
+	}
+
+	/* dqs shift */
+	new_delay = READ_SCC_DQS_IO_OUT2_DELAY;
+	new_delay += delay;
+
+	if (new_delay > IO_IO_OUT2_DELAY_MAX) {
+		debug_cond(DLEVEL == 1, "%s:%d (%u, %u, %u) DQS: %u > %d => %d;"
+			   " adding %u to OUT1\n", __func__, __LINE__,
+			   write_group, group_bgn, delay, new_delay,
+			   IO_IO_OUT2_DELAY_MAX, IO_IO_OUT2_DELAY_MAX,
+			   new_delay - IO_IO_OUT2_DELAY_MAX);
+		scc_mgr_set_dqs_out1_delay(write_group, new_delay -
+					   IO_IO_OUT2_DELAY_MAX);
+		new_delay = IO_IO_OUT2_DELAY_MAX;
+	}
+
+	scc_mgr_load_dqs_io();
+
+	/* oct shift */
+	new_delay = READ_SCC_OCT_OUT2_DELAY;
+	new_delay += delay;
+
+	if (new_delay > IO_IO_OUT2_DELAY_MAX) {
+		debug_cond(DLEVEL == 1, "%s:%d (%u, %u, %u) DQS: %u > %d => %d;"
+			   " adding %u to OUT1\n", __func__, __LINE__,
+			   write_group, group_bgn, delay, new_delay,
+			   IO_IO_OUT2_DELAY_MAX, IO_IO_OUT2_DELAY_MAX,
+			   new_delay - IO_IO_OUT2_DELAY_MAX);
+		scc_mgr_set_oct_out1_delay(write_group, new_delay -
+					   IO_IO_OUT2_DELAY_MAX);
+		new_delay = IO_IO_OUT2_DELAY_MAX;
+	}
+
+	scc_mgr_load_dqs_for_write_group(write_group);
+}
+
+/*
+ * USER apply a delay to the entire output side (DQ, DM, DQS, OCT)
+ * and to all ranks
+ */
+static void scc_mgr_apply_group_all_out_delay_add_all_ranks(
+	uint32_t write_group, uint32_t group_bgn, uint32_t delay)
+{
+	uint32_t r;
+	uint32_t addr = sdr_get_addr(&sdr_scc_mgr->update);
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS;
+		r += NUM_RANKS_PER_SHADOW_REG) {
+		scc_mgr_apply_group_all_out_delay_add(write_group,
+						      group_bgn, delay);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	}
+}
+
+/* optimization used to recover some slots in ddr3 inst_rom */
+/* could be applied to other protocols if we wanted to */
+static void set_jump_as_return(void)
+{
+	uint32_t addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+
+	/*
+	 * to save space, we replace return with jump to special shared
+	 * RETURN instruction so we set the counter to large value so that
+	 * we always jump
+	 */
+	writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+	writel(RW_MGR_RETURN, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+/*
+ * should always use constants as argument to ensure all computations are
+ * performed at compile time
+ */
+static void delay_for_n_mem_clocks(const uint32_t clocks)
+{
+	uint32_t afi_clocks;
+	uint8_t inner = 0;
+	uint8_t outer = 0;
+	uint16_t c_loop = 0;
+	uint32_t addr;
+
+	debug("%s:%d: clocks=%u ... start\n", __func__, __LINE__, clocks);
+
+
+	afi_clocks = (clocks + AFI_RATE_RATIO-1) / AFI_RATE_RATIO;
+	/* scale (rounding up) to get afi clocks */
+
+	/*
+	 * Note, we don't bother accounting for being off a little bit
+	 * because of a few extra instructions in outer loops
+	 * Note, the loops have a test at the end, and do the test before
+	 * the decrement, and so always perform the loop
+	 * 1 time more than the counter value
+	 */
+	if (afi_clocks == 0) {
+		;
+	} else if (afi_clocks <= 0x100) {
+		inner = afi_clocks-1;
+		outer = 0;
+		c_loop = 0;
+	} else if (afi_clocks <= 0x10000) {
+		inner = 0xff;
+		outer = (afi_clocks-1) >> 8;
+		c_loop = 0;
+	} else {
+		inner = 0xff;
+		outer = 0xff;
+		c_loop = (afi_clocks-1) >> 16;
+	}
+
+	/*
+	 * rom instructions are structured as follows:
+	 *
+	 *    IDLE_LOOP2: jnz cntr0, TARGET_A
+	 *    IDLE_LOOP1: jnz cntr1, TARGET_B
+	 *                return
+	 *
+	 * so, when doing nested loops, TARGET_A is set to IDLE_LOOP2, and
+	 * TARGET_B is set to IDLE_LOOP2 as well
+	 *
+	 * if we have no outer loop, though, then we can use IDLE_LOOP1 only,
+	 * and set TARGET_B to IDLE_LOOP1 and we skip IDLE_LOOP2 entirely
+	 *
+	 * a little confusing, but it helps save precious space in the inst_rom
+	 * and sequencer rom and keeps the delays more accurate and reduces
+	 * overhead
+	 */
+	if (afi_clocks <= 0x100) {
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+		writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(inner), SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+		writel(RW_MGR_IDLE_LOOP1, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+		writel(RW_MGR_IDLE_LOOP1, SOCFPGA_SDR_ADDRESS + addr);
+	} else {
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+		writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(inner), SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+		writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(outer), SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+		writel(RW_MGR_IDLE_LOOP2, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+		writel(RW_MGR_IDLE_LOOP2, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* hack to get around compiler not being smart enough */
+		if (afi_clocks <= 0x10000) {
+			/* only need to run once */
+			addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+			writel(RW_MGR_IDLE_LOOP2, SOCFPGA_SDR_ADDRESS + addr);
+		} else {
+			do {
+				addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+				writel(RW_MGR_IDLE_LOOP2, SOCFPGA_SDR_ADDRESS + addr);
+			} while (c_loop-- != 0);
+		}
+	}
+	debug("%s:%d clocks=%u ... end\n", __func__, __LINE__, clocks);
+}
+
+static void rw_mgr_mem_initialize(void)
+{
+	uint32_t r;
+	uint32_t addr;
+
+	debug("%s:%d\n", __func__, __LINE__);
+
+	/* The reset / cke part of initialization is broadcasted to all ranks */
+	addr = sdr_get_addr((u32 *)RW_MGR_SET_CS_AND_ODT_MASK);
+	writel(RW_MGR_RANK_ALL, SOCFPGA_SDR_ADDRESS + addr);
+
+	/*
+	 * Here's how you load register for a loop
+	 * Counters are located @ 0x800
+	 * Jump address are located @ 0xC00
+	 * For both, registers 0 to 3 are selected using bits 3 and 2, like
+	 * in 0x800, 0x804, 0x808, 0x80C and 0xC00, 0xC04, 0xC08, 0xC0C
+	 * I know this ain't pretty, but Avalon bus throws away the 2 least
+	 * significant bits
+	 */
+
+	/* start with memory RESET activated */
+
+	/* tINIT = 200us */
+
+	/*
+	 * 200us @ 266MHz (3.75 ns) ~ 54000 clock cycles
+	 * If a and b are the number of iteration in 2 nested loops
+	 * it takes the following number of cycles to complete the operation:
+	 * number_of_cycles = ((2 + n) * a + 2) * b
+	 * where n is the number of instruction in the inner loop
+	 * One possible solution is n = 0 , a = 256 , b = 106 => a = FF,
+	 * b = 6A
+	 */
+
+	/* Load counters */
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+	writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(SEQ_TINIT_CNTR0_VAL),
+	       SOCFPGA_SDR_ADDRESS + addr);
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+	writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(SEQ_TINIT_CNTR1_VAL),
+	       SOCFPGA_SDR_ADDRESS + addr);
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr2);
+	writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(SEQ_TINIT_CNTR2_VAL),
+	       SOCFPGA_SDR_ADDRESS + addr);
+
+	/* Load jump address */
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+	writel(RW_MGR_INIT_RESET_0_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+	writel(RW_MGR_INIT_RESET_0_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+	writel(RW_MGR_INIT_RESET_0_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* Execute count instruction */
+	addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+	writel(RW_MGR_INIT_RESET_0_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* indicate that memory is stable */
+	addr = sdr_get_addr(&phy_mgr_cfg->reset_mem_stbl);
+	writel(1, SOCFPGA_SDR_ADDRESS + addr);
+
+	/*
+	 * transition the RESET to high
+	 * Wait for 500us
+	 */
+
+	/*
+	 * 500us @ 266MHz (3.75 ns) ~ 134000 clock cycles
+	 * If a and b are the number of iteration in 2 nested loops
+	 * it takes the following number of cycles to complete the operation
+	 * number_of_cycles = ((2 + n) * a + 2) * b
+	 * where n is the number of instruction in the inner loop
+	 * One possible solution is n = 2 , a = 131 , b = 256 => a = 83,
+	 * b = FF
+	 */
+
+	/* Load counters */
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+	writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(SEQ_TRESET_CNTR0_VAL),
+	       SOCFPGA_SDR_ADDRESS + addr);
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+	writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(SEQ_TRESET_CNTR1_VAL),
+	       SOCFPGA_SDR_ADDRESS + addr);
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr2);
+	writel(SKIP_DELAY_LOOP_VALUE_OR_ZERO(SEQ_TRESET_CNTR2_VAL),
+	       SOCFPGA_SDR_ADDRESS + addr);
+
+	/* Load jump address */
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+	writel(RW_MGR_INIT_RESET_1_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+	writel(RW_MGR_INIT_RESET_1_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+	writel(RW_MGR_INIT_RESET_1_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+	writel(RW_MGR_INIT_RESET_1_CKE_0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* bring up clock enable */
+
+	/* tXRP < 250 ck cycles */
+	delay_for_n_mem_clocks(250);
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS; r++) {
+		if (param->skip_ranks[r]) {
+			/* request to skip the rank */
+			continue;
+		}
+
+		/* set rank */
+		set_rank_and_odt_mask(r, RW_MGR_ODT_MODE_OFF);
+
+		/*
+		 * USER Use Mirror-ed commands for odd ranks if address
+		 * mirrorring is on
+		 */
+		if ((RW_MGR_MEM_ADDRESS_MIRRORING >> r) & 0x1) {
+			set_jump_as_return();
+			addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+			writel(RW_MGR_MRS2_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS3_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS1_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS0_DLL_RESET_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+		} else {
+			set_jump_as_return();
+			addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+			writel(RW_MGR_MRS2, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS3, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS1, SOCFPGA_SDR_ADDRESS + addr);
+			set_jump_as_return();
+			writel(RW_MGR_MRS0_DLL_RESET, SOCFPGA_SDR_ADDRESS + addr);
+		}
+		set_jump_as_return();
+		addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+		writel(RW_MGR_ZQCL, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* tZQinit = tDLLK = 512 ck cycles */
+		delay_for_n_mem_clocks(512);
+	}
+}
+
+/*
+ * At the end of calibration we have to program the user settings in, and
+ * USER  hand off the memory to the user.
+ */
+static void rw_mgr_mem_handoff(void)
+{
+	uint32_t r;
+	uint32_t addr;
+
+	debug("%s:%d\n", __func__, __LINE__);
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS; r++) {
+		if (param->skip_ranks[r])
+			/* request to skip the rank */
+			continue;
+		/* set rank */
+		set_rank_and_odt_mask(r, RW_MGR_ODT_MODE_OFF);
+
+		/* precharge all banks ... */
+		addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+		writel(RW_MGR_PRECHARGE_ALL, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* load up MR settings specified by user */
+
+		/*
+		 * Use Mirror-ed commands for odd ranks if address
+		 * mirrorring is on
+		 */
+		addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+		if ((RW_MGR_MEM_ADDRESS_MIRRORING >> r) & 0x1) {
+			set_jump_as_return();
+			writel(RW_MGR_MRS2_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS3_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS1_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS0_USER_MIRR, SOCFPGA_SDR_ADDRESS + addr);
+		} else {
+			set_jump_as_return();
+			writel(RW_MGR_MRS2, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS3, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS1, SOCFPGA_SDR_ADDRESS + addr);
+			delay_for_n_mem_clocks(4);
+			set_jump_as_return();
+			writel(RW_MGR_MRS0_USER, SOCFPGA_SDR_ADDRESS + addr);
+		}
+		/*
+		 * USER  need to wait tMOD (12CK or 15ns) time before issuing
+		 * other commands, but we will have plenty of NIOS cycles before
+		 * actual handoff so its okay.
+		 */
+	}
+}
+
+/*
+ * performs a guaranteed read on the patterns we are going to use during a
+ * read test to ensure memory works
+ */
+static uint32_t rw_mgr_mem_calibrate_read_test_patterns(uint32_t rank_bgn,
+	uint32_t group, uint32_t num_tries, uint32_t *bit_chk,
+	uint32_t all_ranks)
+{
+	uint32_t r, vg;
+	uint32_t correct_mask_vg;
+	uint32_t tmp_bit_chk;
+	uint32_t rank_end = all_ranks ? RW_MGR_MEM_NUMBER_OF_RANKS :
+		(rank_bgn + NUM_RANKS_PER_SHADOW_REG);
+	uint32_t addr;
+	uint32_t base_rw_mgr;
+
+	*bit_chk = param->read_correct_mask;
+	correct_mask_vg = param->read_correct_mask_vg;
+
+	for (r = rank_bgn; r < rank_end; r++) {
+		if (param->skip_ranks[r])
+			/* request to skip the rank */
+			continue;
+
+		/* set rank */
+		set_rank_and_odt_mask(r, RW_MGR_ODT_MODE_READ_WRITE);
+
+		/* Load up a constant bursts of read commands */
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+		writel(0x20, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+		writel(RW_MGR_GUARANTEED_READ, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+		writel(0x20, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+		writel(RW_MGR_GUARANTEED_READ_CONT, SOCFPGA_SDR_ADDRESS + addr);
+
+		tmp_bit_chk = 0;
+		for (vg = RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS-1; ; vg--) {
+			/* reset the fifos to get pointers to known state */
+
+			addr = sdr_get_addr(&phy_mgr_cmd->fifo_reset);
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+			addr = sdr_get_addr((u32 *)RW_MGR_RESET_READ_DATAPATH);
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+			tmp_bit_chk = tmp_bit_chk << (RW_MGR_MEM_DQ_PER_READ_DQS
+				/ RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS);
+
+			addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+			writel(RW_MGR_GUARANTEED_READ, SOCFPGA_SDR_ADDRESS + addr +
+			       ((group * RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS +
+				vg) << 2));
+
+			addr = sdr_get_addr((u32 *)BASE_RW_MGR);
+			base_rw_mgr = readl(SOCFPGA_SDR_ADDRESS + addr);
+			tmp_bit_chk = tmp_bit_chk | (correct_mask_vg & (~base_rw_mgr));
+
+			if (vg == 0)
+				break;
+		}
+		*bit_chk &= tmp_bit_chk;
+	}
+
+	addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+	writel(RW_MGR_CLEAR_DQS_ENABLE, SOCFPGA_SDR_ADDRESS + addr + (group << 2));
+
+	set_rank_and_odt_mask(0, RW_MGR_ODT_MODE_OFF);
+	debug_cond(DLEVEL == 1, "%s:%d test_load_patterns(%u,ALL) => (%u == %u) =>\
+		   %lu\n", __func__, __LINE__, group, *bit_chk, param->read_correct_mask,
+		   (long unsigned int)(*bit_chk == param->read_correct_mask));
+	return *bit_chk == param->read_correct_mask;
+}
+
+static uint32_t rw_mgr_mem_calibrate_read_test_patterns_all_ranks
+	(uint32_t group, uint32_t num_tries, uint32_t *bit_chk)
+{
+	return rw_mgr_mem_calibrate_read_test_patterns(0, group,
+		num_tries, bit_chk, 1);
+}
+
+/* load up the patterns we are going to use during a read test */
+static void rw_mgr_mem_calibrate_read_load_patterns(uint32_t rank_bgn,
+	uint32_t all_ranks)
+{
+	uint32_t r;
+	uint32_t addr;
+	uint32_t rank_end = all_ranks ? RW_MGR_MEM_NUMBER_OF_RANKS :
+		(rank_bgn + NUM_RANKS_PER_SHADOW_REG);
+
+	debug("%s:%d\n", __func__, __LINE__);
+	for (r = rank_bgn; r < rank_end; r++) {
+		if (param->skip_ranks[r])
+			/* request to skip the rank */
+			continue;
+
+		/* set rank */
+		set_rank_and_odt_mask(r, RW_MGR_ODT_MODE_READ_WRITE);
+
+		/* Load up a constant bursts */
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+		writel(0x20, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+		writel(RW_MGR_GUARANTEED_WRITE_WAIT0, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+		writel(0x20, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+		writel(RW_MGR_GUARANTEED_WRITE_WAIT1, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr2);
+		writel(0x04, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+		writel(RW_MGR_GUARANTEED_WRITE_WAIT2, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr3);
+		writel(0x04, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add3);
+		writel(RW_MGR_GUARANTEED_WRITE_WAIT3, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+		writel(RW_MGR_GUARANTEED_WRITE, SOCFPGA_SDR_ADDRESS + addr);
+	}
+
+	set_rank_and_odt_mask(0, RW_MGR_ODT_MODE_OFF);
+}
+
+/*
+ * try a read and see if it returns correct data back. has dummy reads
+ * inserted into the mix used to align dqs enable. has more thorough checks
+ * than the regular read test.
+ */
+static uint32_t rw_mgr_mem_calibrate_read_test(uint32_t rank_bgn, uint32_t group,
+	uint32_t num_tries, uint32_t all_correct, uint32_t *bit_chk,
+	uint32_t all_groups, uint32_t all_ranks)
+{
+	uint32_t r, vg;
+	uint32_t correct_mask_vg;
+	uint32_t tmp_bit_chk;
+	uint32_t rank_end = all_ranks ? RW_MGR_MEM_NUMBER_OF_RANKS :
+		(rank_bgn + NUM_RANKS_PER_SHADOW_REG);
+	uint32_t addr;
+	uint32_t base_rw_mgr;
+
+	*bit_chk = param->read_correct_mask;
+	correct_mask_vg = param->read_correct_mask_vg;
+
+	uint32_t quick_read_mode = (((STATIC_CALIB_STEPS) &
+		CALIB_SKIP_DELAY_SWEEPS) && ENABLE_SUPER_QUICK_CALIBRATION);
+
+	for (r = rank_bgn; r < rank_end; r++) {
+		if (param->skip_ranks[r])
+			/* request to skip the rank */
+			continue;
+
+		/* set rank */
+		set_rank_and_odt_mask(r, RW_MGR_ODT_MODE_READ_WRITE);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+		writel(0x10, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+		writel(RW_MGR_READ_B2B_WAIT1, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr2);
+		writel(0x10, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+		writel(RW_MGR_READ_B2B_WAIT2, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+		if (quick_read_mode)
+			writel(0x1, SOCFPGA_SDR_ADDRESS + addr);
+			/* need at least two (1+1) reads to capture failures */
+		else if (all_groups)
+			writel(0x06, SOCFPGA_SDR_ADDRESS + addr);
+		else
+			writel(0x32, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+		writel(RW_MGR_READ_B2B, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr3);
+		if (all_groups)
+			writel(RW_MGR_MEM_IF_READ_DQS_WIDTH *
+			       RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS - 1,
+			       SOCFPGA_SDR_ADDRESS + addr);
+		else
+			writel(0x0, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add3);
+		writel(RW_MGR_READ_B2B, SOCFPGA_SDR_ADDRESS + addr);
+
+		tmp_bit_chk = 0;
+		for (vg = RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS-1; ; vg--) {
+			/* reset the fifos to get pointers to known state */
+			addr = sdr_get_addr(&phy_mgr_cmd->fifo_reset);
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+			addr = sdr_get_addr((u32 *)RW_MGR_RESET_READ_DATAPATH);
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+			tmp_bit_chk = tmp_bit_chk << (RW_MGR_MEM_DQ_PER_READ_DQS
+				/ RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS);
+
+			addr = sdr_get_addr((u32 *)(all_groups ? RW_MGR_RUN_ALL_GROUPS :
+					    RW_MGR_RUN_SINGLE_GROUP));
+			writel(RW_MGR_READ_B2B, SOCFPGA_SDR_ADDRESS + addr +
+			       ((group * RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS +
+			       vg) << 2));
+
+			addr = sdr_get_addr((u32 *)BASE_RW_MGR);
+			base_rw_mgr = readl(SOCFPGA_SDR_ADDRESS + addr);
+			tmp_bit_chk = tmp_bit_chk | (correct_mask_vg & ~(base_rw_mgr));
+
+			if (vg == 0)
+				break;
+		}
+		*bit_chk &= tmp_bit_chk;
+	}
+
+	addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+	writel(RW_MGR_CLEAR_DQS_ENABLE, SOCFPGA_SDR_ADDRESS + addr + (group << 2));
+
+	if (all_correct) {
+		set_rank_and_odt_mask(0, RW_MGR_ODT_MODE_OFF);
+		debug_cond(DLEVEL == 2, "%s:%d read_test(%u,ALL,%u) =>\
+			   (%u == %u) => %lu", __func__, __LINE__, group,
+			   all_groups, *bit_chk, param->read_correct_mask,
+			   (long unsigned int)(*bit_chk ==
+			   param->read_correct_mask));
+		return *bit_chk == param->read_correct_mask;
+	} else	{
+		set_rank_and_odt_mask(0, RW_MGR_ODT_MODE_OFF);
+		debug_cond(DLEVEL == 2, "%s:%d read_test(%u,ONE,%u) =>\
+			   (%u != %lu) => %lu\n", __func__, __LINE__,
+			   group, all_groups, *bit_chk, (long unsigned int)0,
+			   (long unsigned int)(*bit_chk != 0x00));
+		return *bit_chk != 0x00;
+	}
+}
+
+static uint32_t rw_mgr_mem_calibrate_read_test_all_ranks(uint32_t group,
+	uint32_t num_tries, uint32_t all_correct, uint32_t *bit_chk,
+	uint32_t all_groups)
+{
+	return rw_mgr_mem_calibrate_read_test(0, group, num_tries, all_correct,
+					      bit_chk, all_groups, 1);
+}
+
+static void rw_mgr_incr_vfifo(uint32_t grp, uint32_t *v)
+{
+	uint32_t addr = sdr_get_addr(&phy_mgr_cmd->inc_vfifo_hard_phy);
+
+	writel(grp, SOCFPGA_SDR_ADDRESS + addr);
+	(*v)++;
+}
+
+static void rw_mgr_decr_vfifo(uint32_t grp, uint32_t *v)
+{
+	uint32_t i;
+
+	for (i = 0; i < VFIFO_SIZE-1; i++)
+		rw_mgr_incr_vfifo(grp, v);
+}
+
+static int find_vfifo_read(uint32_t grp, uint32_t *bit_chk)
+{
+	uint32_t  v;
+	uint32_t fail_cnt = 0;
+	uint32_t test_status;
+
+	for (v = 0; v < VFIFO_SIZE; ) {
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: vfifo %u\n",
+			   __func__, __LINE__, v);
+		test_status = rw_mgr_mem_calibrate_read_test_all_ranks
+			(grp, 1, PASS_ONE_BIT, bit_chk, 0);
+		if (!test_status) {
+			fail_cnt++;
+
+			if (fail_cnt == 2)
+				break;
+		}
+
+		/* fiddle with FIFO */
+		rw_mgr_incr_vfifo(grp, &v);
+	}
+
+	if (v >= VFIFO_SIZE) {
+		/* no failing read found!! Something must have gone wrong */
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: vfifo failed\n",
+			   __func__, __LINE__);
+		return 0;
+	} else {
+		return v;
+	}
+}
+
+static int find_working_phase(uint32_t *grp, uint32_t *bit_chk,
+			      uint32_t dtaps_per_ptap, uint32_t *work_bgn,
+			      uint32_t *v, uint32_t *d, uint32_t *p,
+			      uint32_t *i, uint32_t *max_working_cnt)
+{
+	uint32_t found_begin = 0;
+	uint32_t tmp_delay = 0;
+	uint32_t test_status;
+
+	for (*d = 0; *d <= dtaps_per_ptap; (*d)++, tmp_delay +=
+		IO_DELAY_PER_DQS_EN_DCHAIN_TAP) {
+		*work_bgn = tmp_delay;
+		scc_mgr_set_dqs_en_delay_all_ranks(*grp, *d);
+
+		for (*i = 0; *i < VFIFO_SIZE; (*i)++) {
+			for (*p = 0; *p <= IO_DQS_EN_PHASE_MAX; (*p)++, *work_bgn +=
+				IO_DELAY_PER_OPA_TAP) {
+				scc_mgr_set_dqs_en_phase_all_ranks(*grp, *p);
+
+				test_status =
+				rw_mgr_mem_calibrate_read_test_all_ranks
+				(*grp, 1, PASS_ONE_BIT, bit_chk, 0);
+
+				if (test_status) {
+					*max_working_cnt = 1;
+					found_begin = 1;
+					break;
+				}
+			}
+
+			if (found_begin)
+				break;
+
+			if (*p > IO_DQS_EN_PHASE_MAX)
+				/* fiddle with FIFO */
+				rw_mgr_incr_vfifo(*grp, v);
+		}
+
+		if (found_begin)
+			break;
+	}
+
+	if (*i >= VFIFO_SIZE) {
+		/* cannot find working solution */
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: no vfifo/\
+			   ptap/dtap\n", __func__, __LINE__);
+		return 0;
+	} else {
+		return 1;
+	}
+}
+
+static void sdr_backup_phase(uint32_t *grp, uint32_t *bit_chk,
+			     uint32_t *work_bgn, uint32_t *v, uint32_t *d,
+			     uint32_t *p, uint32_t *max_working_cnt)
+{
+	uint32_t found_begin = 0;
+	uint32_t tmp_delay;
+
+	/* Special case code for backing up a phase */
+	if (*p == 0) {
+		*p = IO_DQS_EN_PHASE_MAX;
+		rw_mgr_decr_vfifo(*grp, v);
+	} else {
+		(*p)--;
+	}
+	tmp_delay = *work_bgn - IO_DELAY_PER_OPA_TAP;
+	scc_mgr_set_dqs_en_phase_all_ranks(*grp, *p);
+
+	for (*d = 0; *d <= IO_DQS_EN_DELAY_MAX && tmp_delay < *work_bgn;
+		(*d)++, tmp_delay += IO_DELAY_PER_DQS_EN_DCHAIN_TAP) {
+		scc_mgr_set_dqs_en_delay_all_ranks(*grp, *d);
+
+		if (rw_mgr_mem_calibrate_read_test_all_ranks(*grp, 1,
+							     PASS_ONE_BIT,
+							     bit_chk, 0)) {
+			found_begin = 1;
+			*work_bgn = tmp_delay;
+			break;
+		}
+	}
+
+	/* We have found a working dtap before the ptap found above */
+	if (found_begin == 1)
+		(*max_working_cnt)++;
+
+	/*
+	 * Restore VFIFO to old state before we decremented it
+	 * (if needed).
+	 */
+	(*p)++;
+	if (*p > IO_DQS_EN_PHASE_MAX) {
+		*p = 0;
+		rw_mgr_incr_vfifo(*grp, v);
+	}
+
+	scc_mgr_set_dqs_en_delay_all_ranks(*grp, 0);
+}
+
+static int sdr_nonworking_phase(uint32_t *grp, uint32_t *bit_chk,
+			     uint32_t *work_bgn, uint32_t *v, uint32_t *d,
+			     uint32_t *p, uint32_t *i, uint32_t *max_working_cnt,
+			     uint32_t *work_end)
+{
+	uint32_t found_end = 0;
+
+	(*p)++;
+	*work_end += IO_DELAY_PER_OPA_TAP;
+	if (*p > IO_DQS_EN_PHASE_MAX) {
+		/* fiddle with FIFO */
+		*p = 0;
+		rw_mgr_incr_vfifo(*grp, v);
+	}
+
+	for (; *i < VFIFO_SIZE + 1; (*i)++) {
+		for (; *p <= IO_DQS_EN_PHASE_MAX; (*p)++, *work_end
+			+= IO_DELAY_PER_OPA_TAP) {
+			scc_mgr_set_dqs_en_phase_all_ranks(*grp, *p);
+
+			if (!rw_mgr_mem_calibrate_read_test_all_ranks
+				(*grp, 1, PASS_ONE_BIT, bit_chk, 0)) {
+				found_end = 1;
+				break;
+			} else {
+				(*max_working_cnt)++;
+			}
+		}
+
+		if (found_end)
+			break;
+
+		if (*p > IO_DQS_EN_PHASE_MAX) {
+			/* fiddle with FIFO */
+			rw_mgr_incr_vfifo(*grp, v);
+			*p = 0;
+		}
+	}
+
+	if (*i >= VFIFO_SIZE + 1) {
+		/* cannot see edge of failing read */
+		debug_cond(DLEVEL == 2, "%s:%d sdr_nonworking_phase: end:\
+			   failed\n", __func__, __LINE__);
+		return 0;
+	} else {
+		return 1;
+	}
+}
+
+static int sdr_find_window_centre(uint32_t *grp, uint32_t *bit_chk,
+				  uint32_t *work_bgn, uint32_t *v, uint32_t *d,
+				  uint32_t *p, uint32_t *work_mid,
+				  uint32_t *work_end)
+{
+	int i;
+	int tmp_delay = 0;
+
+	*work_mid = (*work_bgn + *work_end) / 2;
+
+	debug_cond(DLEVEL == 2, "work_bgn=%d work_end=%d work_mid=%d\n",
+		   *work_bgn, *work_end, *work_mid);
+	/* Get the middle delay to be less than a VFIFO delay */
+	for (*p = 0; *p <= IO_DQS_EN_PHASE_MAX;
+		(*p)++, tmp_delay += IO_DELAY_PER_OPA_TAP)
+		;
+	debug_cond(DLEVEL == 2, "vfifo ptap delay %d\n", tmp_delay);
+	while (*work_mid > tmp_delay)
+		*work_mid -= tmp_delay;
+	debug_cond(DLEVEL == 2, "new work_mid %d\n", *work_mid);
+
+	tmp_delay = 0;
+	for (*p = 0; *p <= IO_DQS_EN_PHASE_MAX && tmp_delay < *work_mid;
+		(*p)++, tmp_delay += IO_DELAY_PER_OPA_TAP)
+		;
+	tmp_delay -= IO_DELAY_PER_OPA_TAP;
+	debug_cond(DLEVEL == 2, "new p %d, tmp_delay=%d\n", (*p) - 1, tmp_delay);
+	for (*d = 0; *d <= IO_DQS_EN_DELAY_MAX && tmp_delay < *work_mid; (*d)++,
+		tmp_delay += IO_DELAY_PER_DQS_EN_DCHAIN_TAP)
+		;
+	debug_cond(DLEVEL == 2, "new d %d, tmp_delay=%d\n", *d, tmp_delay);
+
+	scc_mgr_set_dqs_en_phase_all_ranks(*grp, (*p) - 1);
+	scc_mgr_set_dqs_en_delay_all_ranks(*grp, *d);
+
+	/*
+	 * push vfifo until we can successfully calibrate. We can do this
+	 * because the largest possible margin in 1 VFIFO cycle.
+	 */
+	for (i = 0; i < VFIFO_SIZE; i++) {
+		debug_cond(DLEVEL == 2, "find_dqs_en_phase: center: vfifo=%u\n",
+			   *v);
+		if (rw_mgr_mem_calibrate_read_test_all_ranks(*grp, 1,
+							     PASS_ONE_BIT,
+							     bit_chk, 0)) {
+			break;
+		}
+
+		/* fiddle with FIFO */
+		rw_mgr_incr_vfifo(*grp, v);
+	}
+
+	if (i >= VFIFO_SIZE) {
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: center: \
+			   failed\n", __func__, __LINE__);
+		return 0;
+	} else {
+		return 1;
+	}
+}
+
+/* find a good dqs enable to use */
+static uint32_t rw_mgr_mem_calibrate_vfifo_find_dqs_en_phase(uint32_t grp)
+{
+	uint32_t v, d, p, i;
+	uint32_t max_working_cnt;
+	uint32_t bit_chk;
+	uint32_t dtaps_per_ptap;
+	uint32_t work_bgn, work_mid, work_end;
+	uint32_t found_passing_read, found_failing_read, initial_failing_dtap;
+	uint32_t addr;
+
+	debug("%s:%d %u\n", __func__, __LINE__, grp);
+
+	reg_file_set_sub_stage(CAL_SUBSTAGE_VFIFO_CENTER);
+
+	scc_mgr_set_dqs_en_delay_all_ranks(grp, 0);
+	scc_mgr_set_dqs_en_phase_all_ranks(grp, 0);
+
+	/* ************************************************************** */
+	/* * Step 0 : Determine number of delay taps for each phase tap * */
+	dtaps_per_ptap = IO_DELAY_PER_OPA_TAP/IO_DELAY_PER_DQS_EN_DCHAIN_TAP;
+
+	/* ********************************************************* */
+	/* * Step 1 : First push vfifo until we get a failing read * */
+	v = find_vfifo_read(grp, &bit_chk);
+
+	max_working_cnt = 0;
+
+	/* ******************************************************** */
+	/* * step 2: find first working phase, increment in ptaps * */
+	work_bgn = 0;
+	if (find_working_phase(&grp, &bit_chk, dtaps_per_ptap, &work_bgn, &v, &d,
+				&p, &i, &max_working_cnt) == 0)
+		return 0;
+
+	work_end = work_bgn;
+
+	/*
+	 * If d is 0 then the working window covers a phase tap and
+	 * we can follow the old procedure otherwise, we've found the beginning,
+	 * and we need to increment the dtaps until we find the end.
+	 */
+	if (d == 0) {
+		/* ********************************************************* */
+		/* * step 3a: if we have room, back off by one and
+		increment in dtaps * */
+
+		sdr_backup_phase(&grp, &bit_chk, &work_bgn, &v, &d, &p,
+				 &max_working_cnt);
+
+		/* ********************************************************* */
+		/* * step 4a: go forward from working phase to non working
+		phase, increment in ptaps * */
+		if (sdr_nonworking_phase(&grp, &bit_chk, &work_bgn, &v, &d, &p,
+					 &i, &max_working_cnt, &work_end) == 0)
+			return 0;
+
+		/* ********************************************************* */
+		/* * step 5a:  back off one from last, increment in dtaps  * */
+
+		/* Special case code for backing up a phase */
+		if (p == 0) {
+			p = IO_DQS_EN_PHASE_MAX;
+			rw_mgr_decr_vfifo(grp, &v);
+		} else {
+			p = p - 1;
+		}
+
+		work_end -= IO_DELAY_PER_OPA_TAP;
+		scc_mgr_set_dqs_en_phase_all_ranks(grp, p);
+
+		/* * The actual increment of dtaps is done outside of
+		the if/else loop to share code */
+		d = 0;
+
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: v/p: \
+			   vfifo=%u ptap=%u\n", __func__, __LINE__,
+			   v, p);
+	} else {
+		/* ******************************************************* */
+		/* * step 3-5b:  Find the right edge of the window using
+		delay taps   * */
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase:vfifo=%u \
+			   ptap=%u dtap=%u bgn=%u\n", __func__, __LINE__,
+			   v, p, d, work_bgn);
+
+		work_end = work_bgn;
+
+		/* * The actual increment of dtaps is done outside of the
+		if/else loop to share code */
+
+		/* Only here to counterbalance a subtract later on which is
+		not needed if this branch of the algorithm is taken */
+		max_working_cnt++;
+	}
+
+	/* The dtap increment to find the failing edge is done here */
+	for (; d <= IO_DQS_EN_DELAY_MAX; d++, work_end +=
+		IO_DELAY_PER_DQS_EN_DCHAIN_TAP) {
+			debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: \
+				   end-2: dtap=%u\n", __func__, __LINE__, d);
+			scc_mgr_set_dqs_en_delay_all_ranks(grp, d);
+
+			if (!rw_mgr_mem_calibrate_read_test_all_ranks(grp, 1,
+								      PASS_ONE_BIT,
+								      &bit_chk, 0)) {
+				break;
+			}
+	}
+
+	/* Go back to working dtap */
+	if (d != 0)
+		work_end -= IO_DELAY_PER_DQS_EN_DCHAIN_TAP;
+
+	debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: v/p/d: vfifo=%u \
+		   ptap=%u dtap=%u end=%u\n", __func__, __LINE__,
+		   v, p, d-1, work_end);
+
+	if (work_end < work_bgn) {
+		/* nil range */
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: end-2: \
+			   failed\n", __func__, __LINE__);
+		return 0;
+	}
+
+	debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: found range [%u,%u]\n",
+		   __func__, __LINE__, work_bgn, work_end);
+
+	/* *************************************************************** */
+	/*
+	 * * We need to calculate the number of dtaps that equal a ptap
+	 * * To do that we'll back up a ptap and re-find the edge of the
+	 * * window using dtaps
+	 */
+
+	debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: calculate dtaps_per_ptap \
+		   for tracking\n", __func__, __LINE__);
+
+	/* Special case code for backing up a phase */
+	if (p == 0) {
+		p = IO_DQS_EN_PHASE_MAX;
+		rw_mgr_decr_vfifo(grp, &v);
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: backedup \
+			   cycle/phase: v=%u p=%u\n", __func__, __LINE__,
+			   v, p);
+	} else {
+		p = p - 1;
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: backedup \
+			   phase only: v=%u p=%u", __func__, __LINE__,
+			   v, p);
+	}
+
+	scc_mgr_set_dqs_en_phase_all_ranks(grp, p);
+
+	/*
+	 * Increase dtap until we first see a passing read (in case the
+	 * window is smaller than a ptap),
+	 * and then a failing read to mark the edge of the window again
+	 */
+
+	/* Find a passing read */
+	debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: find passing read\n",
+		   __func__, __LINE__);
+	found_passing_read = 0;
+	found_failing_read = 0;
+	initial_failing_dtap = d;
+	for (; d <= IO_DQS_EN_DELAY_MAX; d++) {
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: testing \
+			   read d=%u\n", __func__, __LINE__, d);
+		scc_mgr_set_dqs_en_delay_all_ranks(grp, d);
+
+		if (rw_mgr_mem_calibrate_read_test_all_ranks(grp, 1,
+							     PASS_ONE_BIT,
+							     &bit_chk, 0)) {
+			found_passing_read = 1;
+			break;
+		}
+	}
+
+	if (found_passing_read) {
+		/* Find a failing read */
+		debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: find failing \
+			   read\n", __func__, __LINE__);
+		for (d = d + 1; d <= IO_DQS_EN_DELAY_MAX; d++) {
+			debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: \
+				   testing read d=%u\n", __func__, __LINE__, d);
+			scc_mgr_set_dqs_en_delay_all_ranks(grp, d);
+
+			if (!rw_mgr_mem_calibrate_read_test_all_ranks
+				(grp, 1, PASS_ONE_BIT, &bit_chk, 0)) {
+				found_failing_read = 1;
+				break;
+			}
+		}
+	} else {
+		debug_cond(DLEVEL == 1, "%s:%d find_dqs_en_phase: failed to \
+			   calculate dtaps", __func__, __LINE__);
+		debug_cond(DLEVEL == 1, "per ptap. Fall back on static value\n");
+	}
+
+	/*
+	 * The dynamically calculated dtaps_per_ptap is only valid if we
+	 * found a passing/failing read. If we didn't, it means d hit the max
+	 * (IO_DQS_EN_DELAY_MAX). Otherwise, dtaps_per_ptap retains its
+	 * statically calculated value.
+	 */
+	if (found_passing_read && found_failing_read)
+		dtaps_per_ptap = d - initial_failing_dtap;
+
+	addr = sdr_get_addr(&sdr_reg_file->dtaps_per_ptap);
+	writel(dtaps_per_ptap, SOCFPGA_SDR_ADDRESS + addr);
+	debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: dtaps_per_ptap=%u \
+		   - %u = %u",  __func__, __LINE__, d,
+		   initial_failing_dtap, dtaps_per_ptap);
+
+	/* ******************************************** */
+	/* * step 6:  Find the centre of the window   * */
+	if (sdr_find_window_centre(&grp, &bit_chk, &work_bgn, &v, &d, &p,
+				   &work_mid, &work_end) == 0)
+		return 0;
+
+	debug_cond(DLEVEL == 2, "%s:%d find_dqs_en_phase: center found: \
+		   vfifo=%u ptap=%u dtap=%u\n", __func__, __LINE__,
+		   v, p-1, d);
+	return 1;
+}
+
+/*
+ * Try rw_mgr_mem_calibrate_vfifo_find_dqs_en_phase across different
+ * dq_in_delay values
+ */
+static uint32_t
+rw_mgr_mem_calibrate_vfifo_find_dqs_en_phase_sweep_dq_in_delay
+(uint32_t write_group, uint32_t read_group, uint32_t test_bgn)
+{
+	uint32_t found;
+	uint32_t i;
+	uint32_t p;
+	uint32_t d;
+	uint32_t r;
+	uint32_t addr;
+
+	const uint32_t delay_step = IO_IO_IN_DELAY_MAX /
+		(RW_MGR_MEM_DQ_PER_READ_DQS-1);
+		/* we start at zero, so have one less dq to devide among */
+
+	debug("%s:%d (%u,%u,%u)", __func__, __LINE__, write_group, read_group,
+	      test_bgn);
+
+	/* try different dq_in_delays since the dq path is shorter than dqs */
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS;
+	     r += NUM_RANKS_PER_SHADOW_REG) {
+		for (i = 0, p = test_bgn, d = 0; i < RW_MGR_MEM_DQ_PER_READ_DQS;
+			i++, p++, d += delay_step) {
+			debug_cond(DLEVEL == 1, "%s:%d rw_mgr_mem_calibrate_\
+				   vfifo_find_dqs_", __func__, __LINE__);
+			debug_cond(DLEVEL == 1, "en_phase_sweep_dq_in_delay: g=%u/%u ",
+			       write_group, read_group);
+			debug_cond(DLEVEL == 1, "r=%u, i=%u p=%u d=%u\n", r, i , p, d);
+			scc_mgr_set_dq_in_delay(write_group, p, d);
+			scc_mgr_load_dq(p);
+		}
+		addr = sdr_get_addr(&sdr_scc_mgr->update);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	}
+
+	found = rw_mgr_mem_calibrate_vfifo_find_dqs_en_phase(read_group);
+
+	debug_cond(DLEVEL == 1, "%s:%d rw_mgr_mem_calibrate_vfifo_find_dqs_\
+		   en_phase_sweep_dq", __func__, __LINE__);
+	debug_cond(DLEVEL == 1, "_in_delay: g=%u/%u found=%u; Reseting delay \
+		   chain to zero\n", write_group, read_group, found);
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS;
+	     r += NUM_RANKS_PER_SHADOW_REG) {
+		for (i = 0, p = test_bgn; i < RW_MGR_MEM_DQ_PER_READ_DQS;
+			i++, p++) {
+			scc_mgr_set_dq_in_delay(write_group, p, 0);
+			scc_mgr_load_dq(p);
+		}
+		addr = sdr_get_addr(&sdr_scc_mgr->update);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	}
+
+	return found;
+}
+
+/* per-bit deskew DQ and center */
+static uint32_t rw_mgr_mem_calibrate_vfifo_center(uint32_t rank_bgn,
+	uint32_t write_group, uint32_t read_group, uint32_t test_bgn,
+	uint32_t use_read_test, uint32_t update_fom)
+{
+	uint32_t i, p, d, min_index;
+	/*
+	 * Store these as signed since there are comparisons with
+	 * signed numbers.
+	 */
+	uint32_t bit_chk;
+	uint32_t sticky_bit_chk;
+	int32_t left_edge[RW_MGR_MEM_DQ_PER_READ_DQS];
+	int32_t right_edge[RW_MGR_MEM_DQ_PER_READ_DQS];
+	int32_t final_dq[RW_MGR_MEM_DQ_PER_READ_DQS];
+	int32_t mid;
+	int32_t orig_mid_min, mid_min;
+	int32_t new_dqs, start_dqs, start_dqs_en, shift_dq, final_dqs,
+		final_dqs_en;
+	int32_t dq_margin, dqs_margin;
+	uint32_t stop;
+	uint32_t temp_dq_in_delay1, temp_dq_in_delay2;
+	uint32_t addr;
+
+	debug("%s:%d: %u %u", __func__, __LINE__, read_group, test_bgn);
+
+	addr = sdr_get_addr((u32 *)SCC_MGR_DQS_IN_DELAY);
+	start_dqs = readl(SOCFPGA_SDR_ADDRESS + addr + (read_group << 2));
+	if (IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS)
+		start_dqs_en = readl(SOCFPGA_SDR_ADDRESS + addr + ((read_group << 2)
+				     - IO_DQS_EN_DELAY_OFFSET));
+
+	/* set the left and right edge of each bit to an illegal value */
+	/* use (IO_IO_IN_DELAY_MAX + 1) as an illegal value */
+	sticky_bit_chk = 0;
+	for (i = 0; i < RW_MGR_MEM_DQ_PER_READ_DQS; i++) {
+		left_edge[i]  = IO_IO_IN_DELAY_MAX + 1;
+		right_edge[i] = IO_IO_IN_DELAY_MAX + 1;
+	}
+
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	/* Search for the left edge of the window for each bit */
+	for (d = 0; d <= IO_IO_IN_DELAY_MAX; d++) {
+		scc_mgr_apply_group_dq_in_delay(write_group, test_bgn, d);
+
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+		/*
+		 * Stop searching when the read test doesn't pass AND when
+		 * we've seen a passing read on every bit.
+		 */
+		if (use_read_test) {
+			stop = !rw_mgr_mem_calibrate_read_test(rank_bgn,
+				read_group, NUM_READ_PB_TESTS, PASS_ONE_BIT,
+				&bit_chk, 0, 0);
+		} else {
+			rw_mgr_mem_calibrate_write_test(rank_bgn, write_group,
+							0, PASS_ONE_BIT,
+							&bit_chk, 0);
+			bit_chk = bit_chk >> (RW_MGR_MEM_DQ_PER_READ_DQS *
+				(read_group - (write_group *
+					RW_MGR_MEM_IF_READ_DQS_WIDTH /
+					RW_MGR_MEM_IF_WRITE_DQS_WIDTH)));
+			stop = (bit_chk == 0);
+		}
+		sticky_bit_chk = sticky_bit_chk | bit_chk;
+		stop = stop && (sticky_bit_chk == param->read_correct_mask);
+		debug_cond(DLEVEL == 2, "%s:%d vfifo_center(left): dtap=%u => %u == %u \
+			   && %u", __func__, __LINE__, d,
+			   sticky_bit_chk,
+			param->read_correct_mask, stop);
+
+		if (stop == 1) {
+			break;
+		} else {
+			for (i = 0; i < RW_MGR_MEM_DQ_PER_READ_DQS; i++) {
+				if (bit_chk & 1) {
+					/* Remember a passing test as the
+					left_edge */
+					left_edge[i] = d;
+				} else {
+					/* If a left edge has not been seen yet,
+					then a future passing test will mark
+					this edge as the right edge */
+					if (left_edge[i] ==
+						IO_IO_IN_DELAY_MAX + 1) {
+						right_edge[i] = -(d + 1);
+					}
+				}
+				bit_chk = bit_chk >> 1;
+			}
+		}
+	}
+
+	/* Reset DQ delay chains to 0 */
+	scc_mgr_apply_group_dq_in_delay(write_group, test_bgn, 0);
+	sticky_bit_chk = 0;
+	for (i = RW_MGR_MEM_DQ_PER_READ_DQS - 1;; i--) {
+		debug_cond(DLEVEL == 2, "%s:%d vfifo_center: left_edge[%u]: \
+			   %d right_edge[%u]: %d\n", __func__, __LINE__,
+			   i, left_edge[i], i, right_edge[i]);
+
+		/*
+		 * Check for cases where we haven't found the left edge,
+		 * which makes our assignment of the the right edge invalid.
+		 * Reset it to the illegal value.
+		 */
+		if ((left_edge[i] == IO_IO_IN_DELAY_MAX + 1) && (
+			right_edge[i] != IO_IO_IN_DELAY_MAX + 1)) {
+			right_edge[i] = IO_IO_IN_DELAY_MAX + 1;
+			debug_cond(DLEVEL == 2, "%s:%d vfifo_center: reset \
+				   right_edge[%u]: %d\n", __func__, __LINE__,
+				   i, right_edge[i]);
+		}
+
+		/*
+		 * Reset sticky bit (except for bits where we have seen
+		 * both the left and right edge).
+		 */
+		sticky_bit_chk = sticky_bit_chk << 1;
+		if ((left_edge[i] != IO_IO_IN_DELAY_MAX + 1) &&
+		    (right_edge[i] != IO_IO_IN_DELAY_MAX + 1)) {
+			sticky_bit_chk = sticky_bit_chk | 1;
+		}
+
+		if (i == 0)
+			break;
+	}
+
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	/* Search for the right edge of the window for each bit */
+	for (d = 0; d <= IO_DQS_IN_DELAY_MAX - start_dqs; d++) {
+		scc_mgr_set_dqs_bus_in_delay(read_group, d + start_dqs);
+		if (IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS) {
+			uint32_t delay = d + start_dqs_en;
+			if (delay > IO_DQS_EN_DELAY_MAX)
+				delay = IO_DQS_EN_DELAY_MAX;
+			scc_mgr_set_dqs_en_delay(read_group, delay);
+		}
+		scc_mgr_load_dqs(read_group);
+
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+		/*
+		 * Stop searching when the read test doesn't pass AND when
+		 * we've seen a passing read on every bit.
+		 */
+		if (use_read_test) {
+			stop = !rw_mgr_mem_calibrate_read_test(rank_bgn,
+				read_group, NUM_READ_PB_TESTS, PASS_ONE_BIT,
+				&bit_chk, 0, 0);
+		} else {
+			rw_mgr_mem_calibrate_write_test(rank_bgn, write_group,
+							0, PASS_ONE_BIT,
+							&bit_chk, 0);
+			bit_chk = bit_chk >> (RW_MGR_MEM_DQ_PER_READ_DQS *
+				(read_group - (write_group *
+					RW_MGR_MEM_IF_READ_DQS_WIDTH /
+					RW_MGR_MEM_IF_WRITE_DQS_WIDTH)));
+			stop = (bit_chk == 0);
+		}
+		sticky_bit_chk = sticky_bit_chk | bit_chk;
+		stop = stop && (sticky_bit_chk == param->read_correct_mask);
+
+		debug_cond(DLEVEL == 2, "%s:%d vfifo_center(right): dtap=%u => %u == \
+			   %u && %u", __func__, __LINE__, d,
+			   sticky_bit_chk, param->read_correct_mask, stop);
+
+		if (stop == 1) {
+			break;
+		} else {
+			for (i = 0; i < RW_MGR_MEM_DQ_PER_READ_DQS; i++) {
+				if (bit_chk & 1) {
+					/* Remember a passing test as
+					the right_edge */
+					right_edge[i] = d;
+				} else {
+					if (d != 0) {
+						/* If a right edge has not been
+						seen yet, then a future passing
+						test will mark this edge as the
+						left edge */
+						if (right_edge[i] ==
+						IO_IO_IN_DELAY_MAX + 1) {
+							left_edge[i] = -(d + 1);
+						}
+					} else {
+						/* d = 0 failed, but it passed
+						when testing the left edge,
+						so it must be marginal,
+						set it to -1 */
+						if (right_edge[i] ==
+							IO_IO_IN_DELAY_MAX + 1 &&
+							left_edge[i] !=
+							IO_IO_IN_DELAY_MAX
+							+ 1) {
+							right_edge[i] = -1;
+						}
+						/* If a right edge has not been
+						seen yet, then a future passing
+						test will mark this edge as the
+						left edge */
+						else if (right_edge[i] ==
+							IO_IO_IN_DELAY_MAX +
+							1) {
+							left_edge[i] = -(d + 1);
+						}
+					}
+				}
+
+				debug_cond(DLEVEL == 2, "%s:%d vfifo_center[r,\
+					   d=%u]: ", __func__, __LINE__, d);
+				debug_cond(DLEVEL == 2, "bit_chk_test=%d left_edge[%u]: %d ",
+					   (int)(bit_chk & 1), i, left_edge[i]);
+				debug_cond(DLEVEL == 2, "right_edge[%u]: %d\n", i,
+					   right_edge[i]);
+				bit_chk = bit_chk >> 1;
+			}
+		}
+	}
+
+	/* Check that all bits have a window */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	for (i = 0; i < RW_MGR_MEM_DQ_PER_READ_DQS; i++) {
+		debug_cond(DLEVEL == 2, "%s:%d vfifo_center: left_edge[%u]: \
+			   %d right_edge[%u]: %d", __func__, __LINE__,
+			   i, left_edge[i], i, right_edge[i]);
+		if ((left_edge[i] == IO_IO_IN_DELAY_MAX + 1) || (right_edge[i]
+			== IO_IO_IN_DELAY_MAX + 1)) {
+			/*
+			 * Restore delay chain settings before letting the loop
+			 * in rw_mgr_mem_calibrate_vfifo to retry different
+			 * dqs/ck relationships.
+			 */
+			scc_mgr_set_dqs_bus_in_delay(read_group, start_dqs);
+			if (IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS) {
+				scc_mgr_set_dqs_en_delay(read_group,
+							 start_dqs_en);
+			}
+			scc_mgr_load_dqs(read_group);
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+			debug_cond(DLEVEL == 1, "%s:%d vfifo_center: failed to \
+				   find edge [%u]: %d %d", __func__, __LINE__,
+				   i, left_edge[i], right_edge[i]);
+			if (use_read_test) {
+				set_failing_group_stage(read_group *
+					RW_MGR_MEM_DQ_PER_READ_DQS + i,
+					CAL_STAGE_VFIFO,
+					CAL_SUBSTAGE_VFIFO_CENTER);
+			} else {
+				set_failing_group_stage(read_group *
+					RW_MGR_MEM_DQ_PER_READ_DQS + i,
+					CAL_STAGE_VFIFO_AFTER_WRITES,
+					CAL_SUBSTAGE_VFIFO_CENTER);
+			}
+			return 0;
+		}
+	}
+
+	/* Find middle of window for each DQ bit */
+	mid_min = left_edge[0] - right_edge[0];
+	min_index = 0;
+	for (i = 1; i < RW_MGR_MEM_DQ_PER_READ_DQS; i++) {
+		mid = left_edge[i] - right_edge[i];
+		if (mid < mid_min) {
+			mid_min = mid;
+			min_index = i;
+		}
+	}
+
+	/*
+	 * -mid_min/2 represents the amount that we need to move DQS.
+	 * If mid_min is odd and positive we'll need to add one to
+	 * make sure the rounding in further calculations is correct
+	 * (always bias to the right), so just add 1 for all positive values.
+	 */
+	if (mid_min > 0)
+		mid_min++;
+
+	mid_min = mid_min / 2;
+
+	debug_cond(DLEVEL == 1, "%s:%d vfifo_center: mid_min=%d (index=%u)\n",
+		   __func__, __LINE__, mid_min, min_index);
+
+	/* Determine the amount we can change DQS (which is -mid_min) */
+	orig_mid_min = mid_min;
+	new_dqs = start_dqs - mid_min;
+	if (new_dqs > IO_DQS_IN_DELAY_MAX)
+		new_dqs = IO_DQS_IN_DELAY_MAX;
+	else if (new_dqs < 0)
+		new_dqs = 0;
+
+	mid_min = start_dqs - new_dqs;
+	debug_cond(DLEVEL == 1, "vfifo_center: new mid_min=%d new_dqs=%d\n",
+		   mid_min, new_dqs);
+
+	if (IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS) {
+		if (start_dqs_en - mid_min > IO_DQS_EN_DELAY_MAX)
+			mid_min += start_dqs_en - mid_min - IO_DQS_EN_DELAY_MAX;
+		else if (start_dqs_en - mid_min < 0)
+			mid_min += start_dqs_en - mid_min;
+	}
+	new_dqs = start_dqs - mid_min;
+
+	debug_cond(DLEVEL == 1, "vfifo_center: start_dqs=%d start_dqs_en=%d \
+		   new_dqs=%d mid_min=%d\n", start_dqs,
+		   IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS ? start_dqs_en : -1,
+		   new_dqs, mid_min);
+
+	/* Initialize data for export structures */
+	dqs_margin = IO_IO_IN_DELAY_MAX + 1;
+	dq_margin  = IO_IO_IN_DELAY_MAX + 1;
+
+	addr = sdr_get_addr((u32 *)SCC_MGR_IO_IN_DELAY);
+	/* add delay to bring centre of all DQ windows to the same "level" */
+	for (i = 0, p = test_bgn; i < RW_MGR_MEM_DQ_PER_READ_DQS; i++, p++) {
+		/* Use values before divide by 2 to reduce round off error */
+		shift_dq = (left_edge[i] - right_edge[i] -
+			(left_edge[min_index] - right_edge[min_index]))/2  +
+			(orig_mid_min - mid_min);
+
+		debug_cond(DLEVEL == 2, "vfifo_center: before: \
+			   shift_dq[%u]=%d\n", i, shift_dq);
+
+		temp_dq_in_delay1 = readl(SOCFPGA_SDR_ADDRESS + addr + (p << 2));
+		temp_dq_in_delay2 = readl(SOCFPGA_SDR_ADDRESS + addr + (i << 2));
+
+		if (shift_dq + (int32_t)temp_dq_in_delay1 >
+			(int32_t)IO_IO_IN_DELAY_MAX) {
+			shift_dq = (int32_t)IO_IO_IN_DELAY_MAX - temp_dq_in_delay2;
+		} else if (shift_dq + (int32_t)temp_dq_in_delay1 < 0) {
+			shift_dq = -(int32_t)temp_dq_in_delay1;
+		}
+		debug_cond(DLEVEL == 2, "vfifo_center: after: \
+			   shift_dq[%u]=%d\n", i, shift_dq);
+		final_dq[i] = temp_dq_in_delay1 + shift_dq;
+		scc_mgr_set_dq_in_delay(write_group, p, final_dq[i]);
+		scc_mgr_load_dq(p);
+
+		debug_cond(DLEVEL == 2, "vfifo_center: margin[%u]=[%d,%d]\n", i,
+			   left_edge[i] - shift_dq + (-mid_min),
+			   right_edge[i] + shift_dq - (-mid_min));
+		/* To determine values for export structures */
+		if (left_edge[i] - shift_dq + (-mid_min) < dq_margin)
+			dq_margin = left_edge[i] - shift_dq + (-mid_min);
+
+		if (right_edge[i] + shift_dq - (-mid_min) < dqs_margin)
+			dqs_margin = right_edge[i] + shift_dq - (-mid_min);
+	}
+
+	final_dqs = new_dqs;
+	if (IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS)
+		final_dqs_en = start_dqs_en - mid_min;
+
+	/* Move DQS-en */
+	if (IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS) {
+		scc_mgr_set_dqs_en_delay(read_group, final_dqs_en);
+		scc_mgr_load_dqs(read_group);
+	}
+
+	/* Move DQS */
+	scc_mgr_set_dqs_bus_in_delay(read_group, final_dqs);
+	scc_mgr_load_dqs(read_group);
+	debug_cond(DLEVEL == 2, "%s:%d vfifo_center: dq_margin=%d \
+		   dqs_margin=%d", __func__, __LINE__,
+		   dq_margin, dqs_margin);
+
+	/*
+	 * Do not remove this line as it makes sure all of our decisions
+	 * have been applied. Apply the update bit.
+	 */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	return (dq_margin >= 0) && (dqs_margin >= 0);
+}
+
+/*
+ * calibrate the read valid prediction FIFO.
+ *
+ *  - read valid prediction will consist of finding a good DQS enable phase,
+ * DQS enable delay, DQS input phase, and DQS input delay.
+ *  - we also do a per-bit deskew on the DQ lines.
+ */
+static uint32_t rw_mgr_mem_calibrate_vfifo(uint32_t read_group,
+					   uint32_t test_bgn)
+{
+	uint32_t p, d, rank_bgn, sr;
+	uint32_t dtaps_per_ptap;
+	uint32_t tmp_delay;
+	uint32_t bit_chk;
+	uint32_t grp_calibrated;
+	uint32_t write_group, write_test_bgn;
+	uint32_t failed_substage;
+
+	debug("%s:%d: %u %u", __func__, __LINE__, read_group, test_bgn);
+
+	/* update info for sims */
+	reg_file_set_stage(CAL_STAGE_VFIFO);
+
+	write_group = read_group;
+	write_test_bgn = test_bgn;
+
+	/* USER Determine number of delay taps for each phase tap */
+	dtaps_per_ptap = 0;
+	tmp_delay = 0;
+	while (tmp_delay < IO_DELAY_PER_OPA_TAP) {
+		dtaps_per_ptap++;
+		tmp_delay += IO_DELAY_PER_DQS_EN_DCHAIN_TAP;
+	}
+	dtaps_per_ptap--;
+	tmp_delay = 0;
+
+	/* update info for sims */
+	reg_file_set_group(read_group);
+
+	grp_calibrated = 0;
+
+	reg_file_set_sub_stage(CAL_SUBSTAGE_GUARANTEED_READ);
+	failed_substage = CAL_SUBSTAGE_GUARANTEED_READ;
+
+	for (d = 0; d <= dtaps_per_ptap && grp_calibrated == 0; d += 2) {
+		/*
+		 * In RLDRAMX we may be messing the delay of pins in
+		 * the same write group but outside of the current read
+		 * the group, but that's ok because we haven't
+		 * calibrated output side yet.
+		 */
+		if (d > 0) {
+			scc_mgr_apply_group_all_out_delay_add_all_ranks
+			(write_group, write_test_bgn, d);
+		}
+
+		for (p = 0; p <= IO_DQDQS_OUT_PHASE_MAX && grp_calibrated == 0;
+			p++) {
+			/* set a particular dqdqs phase */
+			scc_mgr_set_dqdqs_output_phase_all_ranks(read_group, p);
+
+			debug_cond(DLEVEL == 1, "%s:%d calibrate_vfifo: g=%u \
+				   p=%u d=%u\n", __func__, __LINE__,
+				   read_group, p, d);
+
+			/*
+			 * Load up the patterns used by read calibration
+			 * using current DQDQS phase.
+			 */
+			rw_mgr_mem_calibrate_read_load_patterns(0, 1);
+			if (!(gbl->phy_debug_mode_flags &
+				PHY_DEBUG_DISABLE_GUARANTEED_READ)) {
+				if (!rw_mgr_mem_calibrate_read_test_patterns_all_ranks
+				    (read_group, 1, &bit_chk)) {
+					debug_cond(DLEVEL == 1, "%s:%d Guaranteed read test failed:",
+						   __func__, __LINE__);
+					debug_cond(DLEVEL == 1, " g=%u p=%u d=%u\n",
+						   read_group, p, d);
+					break;
+				}
+			}
+
+/* case:56390 */
+			grp_calibrated = 1;
+		if (rw_mgr_mem_calibrate_vfifo_find_dqs_en_phase_sweep_dq_in_delay
+		    (write_group, read_group, test_bgn)) {
+				/*
+				 * USER Read per-bit deskew can be done on a
+				 * per shadow register basis.
+				 */
+				for (rank_bgn = 0, sr = 0;
+					rank_bgn < RW_MGR_MEM_NUMBER_OF_RANKS;
+					rank_bgn += NUM_RANKS_PER_SHADOW_REG,
+					++sr) {
+					/*
+					 * Determine if this set of ranks
+					 * should be skipped entirely.
+					 */
+					if (!param->skip_shadow_regs[sr]) {
+						/*
+						 * If doing read after write
+						 * calibration, do not update
+						 * FOM, now - do it then.
+						 */
+					if (!rw_mgr_mem_calibrate_vfifo_center
+						(rank_bgn, write_group,
+						read_group, test_bgn, 1, 0)) {
+							grp_calibrated = 0;
+							failed_substage =
+						CAL_SUBSTAGE_VFIFO_CENTER;
+						}
+					}
+				}
+			} else {
+				grp_calibrated = 0;
+				failed_substage = CAL_SUBSTAGE_DQS_EN_PHASE;
+			}
+		}
+	}
+
+	if (grp_calibrated == 0) {
+		set_failing_group_stage(write_group, CAL_STAGE_VFIFO,
+					failed_substage);
+		return 0;
+	}
+
+	/*
+	 * Reset the delay chains back to zero if they have moved > 1
+	 * (check for > 1 because loop will increase d even when pass in
+	 * first case).
+	 */
+	if (d > 2)
+		scc_mgr_zero_group(write_group, write_test_bgn, 1);
+
+	return 1;
+}
+
+/* VFIFO Calibration -- Read Deskew Calibration after write deskew */
+static uint32_t rw_mgr_mem_calibrate_vfifo_end(uint32_t read_group,
+					       uint32_t test_bgn)
+{
+	uint32_t rank_bgn, sr;
+	uint32_t grp_calibrated;
+	uint32_t write_group;
+
+	debug("%s:%d %u %u", __func__, __LINE__, read_group, test_bgn);
+
+	/* update info for sims */
+
+	reg_file_set_stage(CAL_STAGE_VFIFO_AFTER_WRITES);
+	reg_file_set_sub_stage(CAL_SUBSTAGE_VFIFO_CENTER);
+
+	write_group = read_group;
+
+	/* update info for sims */
+	reg_file_set_group(read_group);
+
+	grp_calibrated = 1;
+	/* Read per-bit deskew can be done on a per shadow register basis */
+	for (rank_bgn = 0, sr = 0; rank_bgn < RW_MGR_MEM_NUMBER_OF_RANKS;
+		rank_bgn += NUM_RANKS_PER_SHADOW_REG, ++sr) {
+		/* Determine if this set of ranks should be skipped entirely */
+		if (!param->skip_shadow_regs[sr]) {
+		/* This is the last calibration round, update FOM here */
+			if (!rw_mgr_mem_calibrate_vfifo_center(rank_bgn,
+								write_group,
+								read_group,
+								test_bgn, 0,
+								1)) {
+				grp_calibrated = 0;
+			}
+		}
+	}
+
+
+	if (grp_calibrated == 0) {
+		set_failing_group_stage(write_group,
+					CAL_STAGE_VFIFO_AFTER_WRITES,
+					CAL_SUBSTAGE_VFIFO_CENTER);
+		return 0;
+	}
+
+	return 1;
+}
+
+/* Calibrate LFIFO to find smallest read latency */
+static uint32_t rw_mgr_mem_calibrate_lfifo(void)
+{
+	uint32_t found_one;
+	uint32_t bit_chk;
+	uint32_t addr;
+
+	debug("%s:%d\n", __func__, __LINE__);
+
+	/* update info for sims */
+	reg_file_set_stage(CAL_STAGE_LFIFO);
+	reg_file_set_sub_stage(CAL_SUBSTAGE_READ_LATENCY);
+
+	/* Load up the patterns used by read calibration for all ranks */
+	rw_mgr_mem_calibrate_read_load_patterns(0, 1);
+	found_one = 0;
+
+	addr = sdr_get_addr(&phy_mgr_cfg->phy_rlat);
+	do {
+		writel(gbl->curr_read_lat, SOCFPGA_SDR_ADDRESS + addr);
+		debug_cond(DLEVEL == 2, "%s:%d lfifo: read_lat=%u",
+			   __func__, __LINE__, gbl->curr_read_lat);
+
+		if (!rw_mgr_mem_calibrate_read_test_all_ranks(0,
+							      NUM_READ_TESTS,
+							      PASS_ALL_BITS,
+							      &bit_chk, 1)) {
+			break;
+		}
+
+		found_one = 1;
+		/* reduce read latency and see if things are working */
+		/* correctly */
+		gbl->curr_read_lat--;
+	} while (gbl->curr_read_lat > 0);
+
+	/* reset the fifos to get pointers to known state */
+
+	addr = sdr_get_addr(&phy_mgr_cmd->fifo_reset);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	if (found_one) {
+		/* add a fudge factor to the read latency that was determined */
+		gbl->curr_read_lat += 2;
+		addr = sdr_get_addr(&phy_mgr_cfg->phy_rlat);
+		writel(gbl->curr_read_lat, SOCFPGA_SDR_ADDRESS + addr);
+		debug_cond(DLEVEL == 2, "%s:%d lfifo: success: using \
+			   read_lat=%u\n", __func__, __LINE__,
+			   gbl->curr_read_lat);
+		return 1;
+	} else {
+		set_failing_group_stage(0xff, CAL_STAGE_LFIFO,
+					CAL_SUBSTAGE_READ_LATENCY);
+
+		debug_cond(DLEVEL == 2, "%s:%d lfifo: failed at initial \
+			   read_lat=%u\n", __func__, __LINE__,
+			   gbl->curr_read_lat);
+		return 0;
+	}
+}
+
+/*
+ * issue write test command.
+ * two variants are provided. one that just tests a write pattern and
+ * another that tests datamask functionality.
+ */
+static void rw_mgr_mem_calibrate_write_test_issue(uint32_t group,
+						  uint32_t test_dm)
+{
+	uint32_t mcc_instruction;
+	uint32_t quick_write_mode = (((STATIC_CALIB_STEPS) & CALIB_SKIP_WRITES) &&
+		ENABLE_SUPER_QUICK_CALIBRATION);
+	uint32_t rw_wl_nop_cycles;
+	uint32_t addr;
+
+	/*
+	 * Set counter and jump addresses for the right
+	 * number of NOP cycles.
+	 * The number of supported NOP cycles can range from -1 to infinity
+	 * Three different cases are handled:
+	 *
+	 * 1. For a number of NOP cycles greater than 0, the RW Mgr looping
+	 *    mechanism will be used to insert the right number of NOPs
+	 *
+	 * 2. For a number of NOP cycles equals to 0, the micro-instruction
+	 *    issuing the write command will jump straight to the
+	 *    micro-instruction that turns on DQS (for DDRx), or outputs write
+	 *    data (for RLD), skipping
+	 *    the NOP micro-instruction all together
+	 *
+	 * 3. A number of NOP cycles equal to -1 indicates that DQS must be
+	 *    turned on in the same micro-instruction that issues the write
+	 *    command. Then we need
+	 *    to directly jump to the micro-instruction that sends out the data
+	 *
+	 * NOTE: Implementing this mechanism uses 2 RW Mgr jump-counters
+	 *       (2 and 3). One jump-counter (0) is used to perform multiple
+	 *       write-read operations.
+	 *       one counter left to issue this command in "multiple-group" mode
+	 */
+
+	rw_wl_nop_cycles = gbl->rw_wl_nop_cycles;
+
+	if (rw_wl_nop_cycles == -1) {
+		/*
+		 * CNTR 2 - We want to execute the special write operation that
+		 * turns on DQS right away and then skip directly to the
+		 * instruction that sends out the data. We set the counter to a
+		 * large number so that the jump is always taken.
+		 */
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr2);
+		writel(0xFF, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* CNTR 3 - Not used */
+		if (test_dm) {
+			mcc_instruction = RW_MGR_LFSR_WR_RD_DM_BANK_0_WL_1;
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+			writel(RW_MGR_LFSR_WR_RD_DM_BANK_0_DATA,
+			       SOCFPGA_SDR_ADDRESS + addr);
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add3);
+			writel(RW_MGR_LFSR_WR_RD_DM_BANK_0_NOP,
+			       SOCFPGA_SDR_ADDRESS + addr);
+		} else {
+			mcc_instruction = RW_MGR_LFSR_WR_RD_BANK_0_WL_1;
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+			writel(RW_MGR_LFSR_WR_RD_BANK_0_DATA, SOCFPGA_SDR_ADDRESS + addr);
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add3);
+			writel(RW_MGR_LFSR_WR_RD_BANK_0_NOP, SOCFPGA_SDR_ADDRESS + addr);
+		}
+	} else if (rw_wl_nop_cycles == 0) {
+		/*
+		 * CNTR 2 - We want to skip the NOP operation and go straight
+		 * to the DQS enable instruction. We set the counter to a large
+		 * number so that the jump is always taken.
+		 */
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr2);
+		writel(0xFF, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* CNTR 3 - Not used */
+		if (test_dm) {
+			mcc_instruction = RW_MGR_LFSR_WR_RD_DM_BANK_0;
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+			writel(RW_MGR_LFSR_WR_RD_DM_BANK_0_DQS,
+			       SOCFPGA_SDR_ADDRESS + addr);
+		} else {
+			mcc_instruction = RW_MGR_LFSR_WR_RD_BANK_0;
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+			writel(RW_MGR_LFSR_WR_RD_BANK_0_DQS, SOCFPGA_SDR_ADDRESS + addr);
+		}
+	} else {
+		/*
+		 * CNTR 2 - In this case we want to execute the next instruction
+		 * and NOT take the jump. So we set the counter to 0. The jump
+		 * address doesn't count.
+		 */
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr2);
+		writel(0x0, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add2);
+		writel(0x0, SOCFPGA_SDR_ADDRESS + addr);
+
+		/*
+		 * CNTR 3 - Set the nop counter to the number of cycles we
+		 * need to loop for, minus 1.
+		 */
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr3);
+		writel(rw_wl_nop_cycles - 1, SOCFPGA_SDR_ADDRESS + addr);
+		if (test_dm) {
+			mcc_instruction = RW_MGR_LFSR_WR_RD_DM_BANK_0;
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add3);
+			writel(RW_MGR_LFSR_WR_RD_DM_BANK_0_NOP, SOCFPGA_SDR_ADDRESS + addr);
+		} else {
+			mcc_instruction = RW_MGR_LFSR_WR_RD_BANK_0;
+			addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add3);
+			writel(RW_MGR_LFSR_WR_RD_BANK_0_NOP, SOCFPGA_SDR_ADDRESS + addr);
+		}
+	}
+
+	addr = sdr_get_addr((u32 *)RW_MGR_RESET_READ_DATAPATH);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+	if (quick_write_mode)
+		writel(0x08, SOCFPGA_SDR_ADDRESS + addr);
+	else
+		writel(0x40, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+	writel(mcc_instruction, SOCFPGA_SDR_ADDRESS + addr);
+
+	/*
+	 * CNTR 1 - This is used to ensure enough time elapses
+	 * for read data to come back.
+	 */
+	addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+	writel(0x30, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+	if (test_dm) {
+		writel(RW_MGR_LFSR_WR_RD_DM_BANK_0_WAIT, SOCFPGA_SDR_ADDRESS + addr);
+	} else {
+		writel(RW_MGR_LFSR_WR_RD_BANK_0_WAIT, SOCFPGA_SDR_ADDRESS + addr);
+	}
+
+	addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+	writel(mcc_instruction, SOCFPGA_SDR_ADDRESS + addr + (group << 2));
+}
+
+/* Test writes, can check for a single bit pass or multiple bit pass */
+static uint32_t rw_mgr_mem_calibrate_write_test(uint32_t rank_bgn,
+	uint32_t write_group, uint32_t use_dm, uint32_t all_correct,
+	uint32_t *bit_chk, uint32_t all_ranks)
+{
+	uint32_t addr;
+	uint32_t r;
+	uint32_t correct_mask_vg;
+	uint32_t tmp_bit_chk;
+	uint32_t vg;
+	uint32_t rank_end = all_ranks ? RW_MGR_MEM_NUMBER_OF_RANKS :
+		(rank_bgn + NUM_RANKS_PER_SHADOW_REG);
+	uint32_t addr_rw_mgr;
+	uint32_t base_rw_mgr;
+
+	*bit_chk = param->write_correct_mask;
+	correct_mask_vg = param->write_correct_mask_vg;
+
+	for (r = rank_bgn; r < rank_end; r++) {
+		if (param->skip_ranks[r]) {
+			/* request to skip the rank */
+			continue;
+		}
+
+		/* set rank */
+		set_rank_and_odt_mask(r, RW_MGR_ODT_MODE_READ_WRITE);
+
+		tmp_bit_chk = 0;
+		addr = sdr_get_addr(&phy_mgr_cmd->fifo_reset);
+		addr_rw_mgr = sdr_get_addr((u32 *)BASE_RW_MGR);
+		for (vg = RW_MGR_MEM_VIRTUAL_GROUPS_PER_WRITE_DQS-1; ; vg--) {
+			/* reset the fifos to get pointers to known state */
+			writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+			tmp_bit_chk = tmp_bit_chk <<
+				(RW_MGR_MEM_DQ_PER_WRITE_DQS /
+				RW_MGR_MEM_VIRTUAL_GROUPS_PER_WRITE_DQS);
+			rw_mgr_mem_calibrate_write_test_issue(write_group *
+				RW_MGR_MEM_VIRTUAL_GROUPS_PER_WRITE_DQS+vg,
+				use_dm);
+
+			base_rw_mgr = readl(SOCFPGA_SDR_ADDRESS + addr_rw_mgr);
+			tmp_bit_chk = tmp_bit_chk | (correct_mask_vg & ~(base_rw_mgr));
+			if (vg == 0)
+				break;
+		}
+		*bit_chk &= tmp_bit_chk;
+	}
+
+	if (all_correct) {
+		set_rank_and_odt_mask(0, RW_MGR_ODT_MODE_OFF);
+		debug_cond(DLEVEL == 2, "write_test(%u,%u,ALL) : %u == \
+			   %u => %lu", write_group, use_dm,
+			   *bit_chk, param->write_correct_mask,
+			   (long unsigned int)(*bit_chk ==
+			   param->write_correct_mask));
+		return *bit_chk == param->write_correct_mask;
+	} else {
+		set_rank_and_odt_mask(0, RW_MGR_ODT_MODE_OFF);
+		debug_cond(DLEVEL == 2, "write_test(%u,%u,ONE) : %u != ",
+		       write_group, use_dm, *bit_chk);
+		debug_cond(DLEVEL == 2, "%lu" " => %lu", (long unsigned int)0,
+			(long unsigned int)(*bit_chk != 0));
+		return *bit_chk != 0x00;
+	}
+}
+
+/*
+ * center all windows. do per-bit-deskew to possibly increase size of
+ * certain windows.
+ */
+static uint32_t rw_mgr_mem_calibrate_writes_center(uint32_t rank_bgn,
+	uint32_t write_group, uint32_t test_bgn)
+{
+	uint32_t i, p, min_index;
+	int32_t d;
+	/*
+	 * Store these as signed since there are comparisons with
+	 * signed numbers.
+	 */
+	uint32_t bit_chk;
+	uint32_t sticky_bit_chk;
+	int32_t left_edge[RW_MGR_MEM_DQ_PER_WRITE_DQS];
+	int32_t right_edge[RW_MGR_MEM_DQ_PER_WRITE_DQS];
+	int32_t mid;
+	int32_t mid_min, orig_mid_min;
+	int32_t new_dqs, start_dqs, shift_dq;
+	int32_t dq_margin, dqs_margin, dm_margin;
+	uint32_t stop;
+	uint32_t temp_dq_out1_delay;
+	uint32_t addr;
+
+	debug("%s:%d %u %u", __func__, __LINE__, write_group, test_bgn);
+
+	dm_margin = 0;
+
+	addr = sdr_get_addr((u32 *)SCC_MGR_IO_OUT1_DELAY);
+	start_dqs = readl(SOCFPGA_SDR_ADDRESS + addr +
+			  (RW_MGR_MEM_DQ_PER_WRITE_DQS << 2));
+
+	/* per-bit deskew */
+
+	/*
+	 * set the left and right edge of each bit to an illegal value
+	 * use (IO_IO_OUT1_DELAY_MAX + 1) as an illegal value.
+	 */
+	sticky_bit_chk = 0;
+	for (i = 0; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++) {
+		left_edge[i]  = IO_IO_OUT1_DELAY_MAX + 1;
+		right_edge[i] = IO_IO_OUT1_DELAY_MAX + 1;
+	}
+
+	/* Search for the left edge of the window for each bit */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	for (d = 0; d <= IO_IO_OUT1_DELAY_MAX; d++) {
+		scc_mgr_apply_group_dq_out1_delay(write_group, test_bgn, d);
+
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+		/*
+		 * Stop searching when the read test doesn't pass AND when
+		 * we've seen a passing read on every bit.
+		 */
+		stop = !rw_mgr_mem_calibrate_write_test(rank_bgn, write_group,
+			0, PASS_ONE_BIT, &bit_chk, 0);
+		sticky_bit_chk = sticky_bit_chk | bit_chk;
+		stop = stop && (sticky_bit_chk == param->write_correct_mask);
+		debug_cond(DLEVEL == 2, "write_center(left): dtap=%d => %u \
+			   == %u && %u [bit_chk= %u ]\n",
+			d, sticky_bit_chk, param->write_correct_mask,
+			stop, bit_chk);
+
+		if (stop == 1) {
+			break;
+		} else {
+			for (i = 0; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++) {
+				if (bit_chk & 1) {
+					/*
+					 * Remember a passing test as the
+					 * left_edge.
+					 */
+					left_edge[i] = d;
+				} else {
+					/*
+					 * If a left edge has not been seen
+					 * yet, then a future passing test will
+					 * mark this edge as the right edge.
+					 */
+					if (left_edge[i] ==
+						IO_IO_OUT1_DELAY_MAX + 1) {
+						right_edge[i] = -(d + 1);
+					}
+				}
+				debug_cond(DLEVEL == 2, "write_center[l,d=%d):", d);
+				debug_cond(DLEVEL == 2, "bit_chk_test=%d left_edge[%u]: %d",
+					   (int)(bit_chk & 1), i, left_edge[i]);
+				debug_cond(DLEVEL == 2, "right_edge[%u]: %d\n", i,
+				       right_edge[i]);
+				bit_chk = bit_chk >> 1;
+			}
+		}
+	}
+
+	/* Reset DQ delay chains to 0 */
+	scc_mgr_apply_group_dq_out1_delay(write_group, test_bgn, 0);
+	sticky_bit_chk = 0;
+	for (i = RW_MGR_MEM_DQ_PER_WRITE_DQS - 1;; i--) {
+		debug_cond(DLEVEL == 2, "%s:%d write_center: left_edge[%u]: \
+			   %d right_edge[%u]: %d\n", __func__, __LINE__,
+			   i, left_edge[i], i, right_edge[i]);
+
+		/*
+		 * Check for cases where we haven't found the left edge,
+		 * which makes our assignment of the the right edge invalid.
+		 * Reset it to the illegal value.
+		 */
+		if ((left_edge[i] == IO_IO_OUT1_DELAY_MAX + 1) &&
+		    (right_edge[i] != IO_IO_OUT1_DELAY_MAX + 1)) {
+			right_edge[i] = IO_IO_OUT1_DELAY_MAX + 1;
+			debug_cond(DLEVEL == 2, "%s:%d write_center: reset \
+				   right_edge[%u]: %d\n", __func__, __LINE__,
+				   i, right_edge[i]);
+		}
+
+		/*
+		 * Reset sticky bit (except for bits where we have
+		 * seen the left edge).
+		 */
+		sticky_bit_chk = sticky_bit_chk << 1;
+		if ((left_edge[i] != IO_IO_OUT1_DELAY_MAX + 1))
+			sticky_bit_chk = sticky_bit_chk | 1;
+
+		if (i == 0)
+			break;
+	}
+
+	/* Search for the right edge of the window for each bit */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	for (d = 0; d <= IO_IO_OUT1_DELAY_MAX - start_dqs; d++) {
+		scc_mgr_apply_group_dqs_io_and_oct_out1(write_group,
+							d + start_dqs);
+
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+		/*
+		 * Stop searching when the read test doesn't pass AND when
+		 * we've seen a passing read on every bit.
+		 */
+		stop = !rw_mgr_mem_calibrate_write_test(rank_bgn, write_group,
+			0, PASS_ONE_BIT, &bit_chk, 0);
+
+		sticky_bit_chk = sticky_bit_chk | bit_chk;
+		stop = stop && (sticky_bit_chk == param->write_correct_mask);
+
+		debug_cond(DLEVEL == 2, "write_center (right): dtap=%u => %u == \
+			   %u && %u\n", d, sticky_bit_chk,
+			   param->write_correct_mask, stop);
+
+		if (stop == 1) {
+			if (d == 0) {
+				for (i = 0; i < RW_MGR_MEM_DQ_PER_WRITE_DQS;
+					i++) {
+					/* d = 0 failed, but it passed when
+					testing the left edge, so it must be
+					marginal, set it to -1 */
+					if (right_edge[i] ==
+						IO_IO_OUT1_DELAY_MAX + 1 &&
+						left_edge[i] !=
+						IO_IO_OUT1_DELAY_MAX + 1) {
+						right_edge[i] = -1;
+					}
+				}
+			}
+			break;
+		} else {
+			for (i = 0; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++) {
+				if (bit_chk & 1) {
+					/*
+					 * Remember a passing test as
+					 * the right_edge.
+					 */
+					right_edge[i] = d;
+				} else {
+					if (d != 0) {
+						/*
+						 * If a right edge has not
+						 * been seen yet, then a future
+						 * passing test will mark this
+						 * edge as the left edge.
+						 */
+						if (right_edge[i] ==
+						    IO_IO_OUT1_DELAY_MAX + 1)
+							left_edge[i] = -(d + 1);
+					} else {
+						/*
+						 * d = 0 failed, but it passed
+						 * when testing the left edge,
+						 * so it must be marginal, set
+						 * it to -1.
+						 */
+						if (right_edge[i] ==
+						    IO_IO_OUT1_DELAY_MAX + 1 &&
+						    left_edge[i] !=
+						    IO_IO_OUT1_DELAY_MAX + 1)
+							right_edge[i] = -1;
+						/*
+						 * If a right edge has not been
+						 * seen yet, then a future
+						 * passing test will mark this
+						 * edge as the left edge.
+						 */
+						else if (right_edge[i] ==
+							IO_IO_OUT1_DELAY_MAX +
+							1)
+							left_edge[i] = -(d + 1);
+					}
+				}
+				debug_cond(DLEVEL == 2, "write_center[r,d=%d):", d);
+				debug_cond(DLEVEL == 2, "bit_chk_test=%d left_edge[%u]: %d",
+					   (int)(bit_chk & 1), i, left_edge[i]);
+				debug_cond(DLEVEL == 2, "right_edge[%u]: %d\n", i,
+					   right_edge[i]);
+				bit_chk = bit_chk >> 1;
+			}
+		}
+	}
+
+	/* Check that all bits have a window */
+	for (i = 0; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++) {
+		debug_cond(DLEVEL == 2, "%s:%d write_center: left_edge[%u]: \
+			   %d right_edge[%u]: %d", __func__, __LINE__,
+			   i, left_edge[i], i, right_edge[i]);
+		if ((left_edge[i] == IO_IO_OUT1_DELAY_MAX + 1) ||
+		    (right_edge[i] == IO_IO_OUT1_DELAY_MAX + 1)) {
+			set_failing_group_stage(test_bgn + i,
+						CAL_STAGE_WRITES,
+						CAL_SUBSTAGE_WRITES_CENTER);
+			return 0;
+		}
+	}
+
+	/* Find middle of window for each DQ bit */
+	mid_min = left_edge[0] - right_edge[0];
+	min_index = 0;
+	for (i = 1; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++) {
+		mid = left_edge[i] - right_edge[i];
+		if (mid < mid_min) {
+			mid_min = mid;
+			min_index = i;
+		}
+	}
+
+	/*
+	 * -mid_min/2 represents the amount that we need to move DQS.
+	 * If mid_min is odd and positive we'll need to add one to
+	 * make sure the rounding in further calculations is correct
+	 * (always bias to the right), so just add 1 for all positive values.
+	 */
+	if (mid_min > 0)
+		mid_min++;
+	mid_min = mid_min / 2;
+	debug_cond(DLEVEL == 1, "%s:%d write_center: mid_min=%d\n", __func__,
+		   __LINE__, mid_min);
+
+	/* Determine the amount we can change DQS (which is -mid_min) */
+	orig_mid_min = mid_min;
+	new_dqs = start_dqs;
+	mid_min = 0;
+	debug_cond(DLEVEL == 1, "%s:%d write_center: start_dqs=%d new_dqs=%d \
+		   mid_min=%d\n", __func__, __LINE__, start_dqs, new_dqs, mid_min);
+	/* Initialize data for export structures */
+	dqs_margin = IO_IO_OUT1_DELAY_MAX + 1;
+	dq_margin  = IO_IO_OUT1_DELAY_MAX + 1;
+
+	/* add delay to bring centre of all DQ windows to the same "level" */
+	addr = sdr_get_addr((u32 *)SCC_MGR_IO_OUT1_DELAY);
+	for (i = 0, p = test_bgn; i < RW_MGR_MEM_DQ_PER_WRITE_DQS; i++, p++) {
+		/* Use values before divide by 2 to reduce round off error */
+		shift_dq = (left_edge[i] - right_edge[i] -
+			(left_edge[min_index] - right_edge[min_index]))/2  +
+		(orig_mid_min - mid_min);
+
+		debug_cond(DLEVEL == 2, "%s:%d write_center: before: shift_dq \
+			   [%u]=%d\n", __func__, __LINE__, i, shift_dq);
+
+		temp_dq_out1_delay = readl(SOCFPGA_SDR_ADDRESS + addr + (i << 2));
+		if (shift_dq + (int32_t)temp_dq_out1_delay >
+			(int32_t)IO_IO_OUT1_DELAY_MAX) {
+			shift_dq = (int32_t)IO_IO_OUT1_DELAY_MAX - temp_dq_out1_delay;
+		} else if (shift_dq + (int32_t)temp_dq_out1_delay < 0) {
+			shift_dq = -(int32_t)temp_dq_out1_delay;
+		}
+		debug_cond(DLEVEL == 2, "write_center: after: shift_dq[%u]=%d\n",
+			   i, shift_dq);
+		scc_mgr_set_dq_out1_delay(write_group, i, temp_dq_out1_delay +
+					  shift_dq);
+		scc_mgr_load_dq(i);
+
+		debug_cond(DLEVEL == 2, "write_center: margin[%u]=[%d,%d]\n", i,
+			   left_edge[i] - shift_dq + (-mid_min),
+			   right_edge[i] + shift_dq - (-mid_min));
+		/* To determine values for export structures */
+		if (left_edge[i] - shift_dq + (-mid_min) < dq_margin)
+			dq_margin = left_edge[i] - shift_dq + (-mid_min);
+
+		if (right_edge[i] + shift_dq - (-mid_min) < dqs_margin)
+			dqs_margin = right_edge[i] + shift_dq - (-mid_min);
+	}
+
+	/* Move DQS */
+	scc_mgr_apply_group_dqs_io_and_oct_out1(write_group, new_dqs);
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* Centre DM */
+	debug_cond(DLEVEL == 2, "%s:%d write_center: DM\n", __func__, __LINE__);
+
+	/*
+	 * set the left and right edge of each bit to an illegal value,
+	 * use (IO_IO_OUT1_DELAY_MAX + 1) as an illegal value,
+	 */
+	left_edge[0]  = IO_IO_OUT1_DELAY_MAX + 1;
+	right_edge[0] = IO_IO_OUT1_DELAY_MAX + 1;
+	int32_t bgn_curr = IO_IO_OUT1_DELAY_MAX + 1;
+	int32_t end_curr = IO_IO_OUT1_DELAY_MAX + 1;
+	int32_t bgn_best = IO_IO_OUT1_DELAY_MAX + 1;
+	int32_t end_best = IO_IO_OUT1_DELAY_MAX + 1;
+	int32_t win_best = 0;
+
+	/* Search for the/part of the window with DM shift */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	for (d = IO_IO_OUT1_DELAY_MAX; d >= 0; d -= DELTA_D) {
+		scc_mgr_apply_group_dm_out1_delay(write_group, d);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+		if (rw_mgr_mem_calibrate_write_test(rank_bgn, write_group, 1,
+						    PASS_ALL_BITS, &bit_chk,
+						    0)) {
+			/* USE Set current end of the window */
+			end_curr = -d;
+			/*
+			 * If a starting edge of our window has not been seen
+			 * this is our current start of the DM window.
+			 */
+			if (bgn_curr == IO_IO_OUT1_DELAY_MAX + 1)
+				bgn_curr = -d;
+
+			/*
+			 * If current window is bigger than best seen.
+			 * Set best seen to be current window.
+			 */
+			if ((end_curr-bgn_curr+1) > win_best) {
+				win_best = end_curr-bgn_curr+1;
+				bgn_best = bgn_curr;
+				end_best = end_curr;
+			}
+		} else {
+			/* We just saw a failing test. Reset temp edge */
+			bgn_curr = IO_IO_OUT1_DELAY_MAX + 1;
+			end_curr = IO_IO_OUT1_DELAY_MAX + 1;
+			}
+		}
+
+
+	/* Reset DM delay chains to 0 */
+	scc_mgr_apply_group_dm_out1_delay(write_group, 0);
+
+	/*
+	 * Check to see if the current window nudges up aganist 0 delay.
+	 * If so we need to continue the search by shifting DQS otherwise DQS
+	 * search begins as a new search. */
+	if (end_curr != 0) {
+		bgn_curr = IO_IO_OUT1_DELAY_MAX + 1;
+		end_curr = IO_IO_OUT1_DELAY_MAX + 1;
+	}
+
+	/* Search for the/part of the window with DQS shifts */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	for (d = 0; d <= IO_IO_OUT1_DELAY_MAX - new_dqs; d += DELTA_D) {
+		/*
+		 * Note: This only shifts DQS, so are we limiting ourselve to
+		 * width of DQ unnecessarily.
+		 */
+		scc_mgr_apply_group_dqs_io_and_oct_out1(write_group,
+							d + new_dqs);
+
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+		if (rw_mgr_mem_calibrate_write_test(rank_bgn, write_group, 1,
+						    PASS_ALL_BITS, &bit_chk,
+						    0)) {
+			/* USE Set current end of the window */
+			end_curr = d;
+			/*
+			 * If a beginning edge of our window has not been seen
+			 * this is our current begin of the DM window.
+			 */
+			if (bgn_curr == IO_IO_OUT1_DELAY_MAX + 1)
+				bgn_curr = d;
+
+			/*
+			 * If current window is bigger than best seen. Set best
+			 * seen to be current window.
+			 */
+			if ((end_curr-bgn_curr+1) > win_best) {
+				win_best = end_curr-bgn_curr+1;
+				bgn_best = bgn_curr;
+				end_best = end_curr;
+			}
+		} else {
+			/* We just saw a failing test. Reset temp edge */
+			bgn_curr = IO_IO_OUT1_DELAY_MAX + 1;
+			end_curr = IO_IO_OUT1_DELAY_MAX + 1;
+
+			/* Early exit optimization: if ther remaining delay
+			chain space is less than already seen largest window
+			we can exit */
+			if ((win_best-1) >
+				(IO_IO_OUT1_DELAY_MAX - new_dqs - d)) {
+					break;
+				}
+			}
+		}
+
+	/* assign left and right edge for cal and reporting; */
+	left_edge[0] = -1*bgn_best;
+	right_edge[0] = end_best;
+
+	debug_cond(DLEVEL == 2, "%s:%d dm_calib: left=%d right=%d\n", __func__,
+		   __LINE__, left_edge[0], right_edge[0]);
+
+	/* Move DQS (back to orig) */
+	scc_mgr_apply_group_dqs_io_and_oct_out1(write_group, new_dqs);
+
+	/* Move DM */
+
+	/* Find middle of window for the DM bit */
+	mid = (left_edge[0] - right_edge[0]) / 2;
+
+	/* only move right, since we are not moving DQS/DQ */
+	if (mid < 0)
+		mid = 0;
+
+	/* dm_marign should fail if we never find a window */
+	if (win_best == 0)
+		dm_margin = -1;
+	else
+		dm_margin = left_edge[0] - mid;
+
+	scc_mgr_apply_group_dm_out1_delay(write_group, mid);
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	debug_cond(DLEVEL == 2, "%s:%d dm_calib: left=%d right=%d mid=%d \
+		   dm_margin=%d\n", __func__, __LINE__, left_edge[0],
+		   right_edge[0], mid, dm_margin);
+	/* Export values */
+	gbl->fom_out += dq_margin + dqs_margin;
+
+	debug_cond(DLEVEL == 2, "%s:%d write_center: dq_margin=%d \
+		   dqs_margin=%d dm_margin=%d\n", __func__, __LINE__,
+		   dq_margin, dqs_margin, dm_margin);
+
+	/*
+	 * Do not remove this line as it makes sure all of our
+	 * decisions have been applied.
+	 */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	return (dq_margin >= 0) && (dqs_margin >= 0) && (dm_margin >= 0);
+}
+
+/* calibrate the write operations */
+static uint32_t rw_mgr_mem_calibrate_writes(uint32_t rank_bgn, uint32_t g,
+	uint32_t test_bgn)
+{
+	/* update info for sims */
+	debug("%s:%d %u %u\n", __func__, __LINE__, g, test_bgn);
+
+	reg_file_set_stage(CAL_STAGE_WRITES);
+	reg_file_set_sub_stage(CAL_SUBSTAGE_WRITES_CENTER);
+
+	reg_file_set_group(g);
+
+	if (!rw_mgr_mem_calibrate_writes_center(rank_bgn, g, test_bgn)) {
+		set_failing_group_stage(g, CAL_STAGE_WRITES,
+					CAL_SUBSTAGE_WRITES_CENTER);
+		return 0;
+	}
+
+	return 1;
+}
+
+/* precharge all banks and activate row 0 in bank "000..." and bank "111..." */
+static void mem_precharge_and_activate(void)
+{
+	uint32_t r;
+	uint32_t addr;
+
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS; r++) {
+		if (param->skip_ranks[r]) {
+			/* request to skip the rank */
+			continue;
+		}
+
+		/* set rank */
+		set_rank_and_odt_mask(r, RW_MGR_ODT_MODE_OFF);
+
+		/* precharge all banks ... */
+		addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+		writel(RW_MGR_PRECHARGE_ALL, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr0);
+		writel(0x0F, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add0);
+		writel(RW_MGR_ACTIVATE_0_AND_1_WAIT1, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&sdr_rw_load_mgr_regs->load_cntr1);
+		writel(0x0F, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_rw_load_jump_mgr_regs->load_jump_add1);
+		writel(RW_MGR_ACTIVATE_0_AND_1_WAIT2, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* activate rows */
+		addr = sdr_get_addr((u32 *)RW_MGR_RUN_SINGLE_GROUP);
+		writel(RW_MGR_ACTIVATE_0_AND_1, SOCFPGA_SDR_ADDRESS + addr);
+	}
+}
+
+/* Configure various memory related parameters. */
+static void mem_config(void)
+{
+	uint32_t rlat, wlat;
+	uint32_t rw_wl_nop_cycles;
+	uint32_t max_latency;
+	uint32_t addr;
+
+	debug("%s:%d\n", __func__, __LINE__);
+	/* read in write and read latency */
+	addr = sdr_get_addr(&data_mgr->t_wl_add);
+	wlat = readl(SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&data_mgr->mem_t_add);
+	wlat += readl(SOCFPGA_SDR_ADDRESS + addr);
+	/* WL for hard phy does not include additive latency */
+
+	/*
+	 * add addtional write latency to offset the address/command extra
+	 * clock cycle. We change the AC mux setting causing AC to be delayed
+	 * by one mem clock cycle. Only do this for DDR3
+	 */
+	wlat = wlat + 1;
+
+	addr = sdr_get_addr(&data_mgr->t_rl_add);
+	rlat = readl(SOCFPGA_SDR_ADDRESS + addr);
+
+	rw_wl_nop_cycles = wlat - 2;
+	gbl->rw_wl_nop_cycles = rw_wl_nop_cycles;
+
+	/*
+	 * For AV/CV, lfifo is hardened and always runs at full rate so
+	 * max latency in AFI clocks, used here, is correspondingly smaller.
+	 */
+	max_latency = (1<<MAX_LATENCY_COUNT_WIDTH)/1 - 1;
+	/* configure for a burst length of 8 */
+
+	/* write latency */
+	/* Adjust Write Latency for Hard PHY */
+	wlat = wlat + 1;
+
+	/* set a pretty high read latency initially */
+	gbl->curr_read_lat = rlat + 16;
+
+	if (gbl->curr_read_lat > max_latency)
+		gbl->curr_read_lat = max_latency;
+
+	addr = sdr_get_addr(&phy_mgr_cfg->phy_rlat);
+	writel(gbl->curr_read_lat, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* advertise write latency */
+	gbl->curr_write_lat = wlat;
+	addr = sdr_get_addr(&phy_mgr_cfg->afi_wlat);
+	writel(wlat - 2, SOCFPGA_SDR_ADDRESS + addr);
+
+	/* initialize bit slips */
+	mem_precharge_and_activate();
+}
+
+/* Set VFIFO and LFIFO to instant-on settings in skip calibration mode */
+static void mem_skip_calibrate(void)
+{
+	uint32_t vfifo_offset;
+	uint32_t i, j, r;
+	uint32_t addr;
+
+	debug("%s:%d\n", __func__, __LINE__);
+	/* Need to update every shadow register set used by the interface */
+	for (r = 0; r < RW_MGR_MEM_NUMBER_OF_RANKS;
+		r += NUM_RANKS_PER_SHADOW_REG) {
+		/*
+		 * Set output phase alignment settings appropriate for
+		 * skip calibration.
+		 */
+		for (i = 0; i < RW_MGR_MEM_IF_READ_DQS_WIDTH; i++) {
+			scc_mgr_set_dqs_en_phase(i, 0);
+#if IO_DLL_CHAIN_LENGTH == 6
+			scc_mgr_set_dqdqs_output_phase(i, 6);
+#else
+			scc_mgr_set_dqdqs_output_phase(i, 7);
+#endif
+			/*
+			 * Case:33398
+			 *
+			 * Write data arrives to the I/O two cycles before write
+			 * latency is reached (720 deg).
+			 *   -> due to bit-slip in a/c bus
+			 *   -> to allow board skew where dqs is longer than ck
+			 *      -> how often can this happen!?
+			 *      -> can claim back some ptaps for high freq
+			 *       support if we can relax this, but i digress...
+			 *
+			 * The write_clk leads mem_ck by 90 deg
+			 * The minimum ptap of the OPA is 180 deg
+			 * Each ptap has (360 / IO_DLL_CHAIN_LENGH) deg of delay
+			 * The write_clk is always delayed by 2 ptaps
+			 *
+			 * Hence, to make DQS aligned to CK, we need to delay
+			 * DQS by:
+			 *    (720 - 90 - 180 - 2 * (360 / IO_DLL_CHAIN_LENGTH))
+			 *
+			 * Dividing the above by (360 / IO_DLL_CHAIN_LENGTH)
+			 * gives us the number of ptaps, which simplies to:
+			 *
+			 *    (1.25 * IO_DLL_CHAIN_LENGTH - 2)
+			 */
+			scc_mgr_set_dqdqs_output_phase(i, (1.25 *
+				IO_DLL_CHAIN_LENGTH - 2));
+		}
+		addr = sdr_get_addr(&sdr_scc_mgr->dqs_ena);
+		writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_scc_mgr->dqs_io_ena);
+		writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr((u32 *)SCC_MGR_GROUP_COUNTER);
+		for (i = 0; i < RW_MGR_MEM_IF_WRITE_DQS_WIDTH; i++) {
+			writel(i, SOCFPGA_SDR_ADDRESS + addr);
+		}
+		addr = sdr_get_addr(&sdr_scc_mgr->dq_ena);
+		writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_scc_mgr->dm_ena);
+		writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&sdr_scc_mgr->update);
+		writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	}
+
+	/* Compensate for simulation model behaviour */
+	for (i = 0; i < RW_MGR_MEM_IF_READ_DQS_WIDTH; i++) {
+		scc_mgr_set_dqs_bus_in_delay(i, 10);
+		scc_mgr_load_dqs(i);
+	}
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/*
+	 * ArriaV has hard FIFOs that can only be initialized by incrementing
+	 * in sequencer.
+	 */
+	vfifo_offset = CALIB_VFIFO_OFFSET;
+	addr = sdr_get_addr(&phy_mgr_cmd->inc_vfifo_hard_phy);
+	for (j = 0; j < vfifo_offset; j++) {
+		writel(0xff, SOCFPGA_SDR_ADDRESS + addr);
+	}
+	addr = sdr_get_addr(&phy_mgr_cmd->fifo_reset);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/*
+	 * For ACV with hard lfifo, we get the skip-cal setting from
+	 * generation-time constant.
+	 */
+	gbl->curr_read_lat = CALIB_LFIFO_OFFSET;
+	addr = sdr_get_addr(&phy_mgr_cfg->phy_rlat);
+	writel(gbl->curr_read_lat, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+/* Memory calibration entry point */
+static uint32_t mem_calibrate(void)
+{
+	uint32_t i;
+	uint32_t rank_bgn, sr;
+	uint32_t write_group, write_test_bgn;
+	uint32_t read_group, read_test_bgn;
+	uint32_t run_groups, current_run;
+	uint32_t failing_groups = 0;
+	uint32_t group_failed = 0;
+	uint32_t sr_failed = 0;
+	uint32_t addr;
+
+	debug("%s:%d\n", __func__, __LINE__);
+	/* Initialize the data settings */
+
+	gbl->error_substage = CAL_SUBSTAGE_NIL;
+	gbl->error_stage = CAL_STAGE_NIL;
+	gbl->error_group = 0xff;
+	gbl->fom_in = 0;
+	gbl->fom_out = 0;
+
+	mem_config();
+
+	uint32_t bypass_mode = 0x1;
+	addr = sdr_get_addr((u32 *)SCC_MGR_GROUP_COUNTER);
+	for (i = 0; i < RW_MGR_MEM_IF_READ_DQS_WIDTH; i++) {
+		writel(i, SOCFPGA_SDR_ADDRESS + addr);
+		scc_set_bypass_mode(i, bypass_mode);
+	}
+
+	if ((dyn_calib_steps & CALIB_SKIP_ALL) == CALIB_SKIP_ALL) {
+		/*
+		 * Set VFIFO and LFIFO to instant-on settings in skip
+		 * calibration mode.
+		 */
+		mem_skip_calibrate();
+	} else {
+		for (i = 0; i < NUM_CALIB_REPEAT; i++) {
+			/*
+			 * Zero all delay chain/phase settings for all
+			 * groups and all shadow register sets.
+			 */
+			scc_mgr_zero_all();
+
+			run_groups = ~param->skip_groups;
+
+			for (write_group = 0, write_test_bgn = 0; write_group
+				< RW_MGR_MEM_IF_WRITE_DQS_WIDTH; write_group++,
+				write_test_bgn += RW_MGR_MEM_DQ_PER_WRITE_DQS) {
+				/* Initialized the group failure */
+				group_failed = 0;
+
+				current_run = run_groups & ((1 <<
+					RW_MGR_NUM_DQS_PER_WRITE_GROUP) - 1);
+				run_groups = run_groups >>
+					RW_MGR_NUM_DQS_PER_WRITE_GROUP;
+
+				if (current_run == 0)
+					continue;
+
+				addr = sdr_get_addr((u32 *)SCC_MGR_GROUP_COUNTER);
+				writel(write_group, SOCFPGA_SDR_ADDRESS + addr);
+				scc_mgr_zero_group(write_group, write_test_bgn,
+						   0);
+
+				for (read_group = write_group *
+					RW_MGR_MEM_IF_READ_DQS_WIDTH /
+					RW_MGR_MEM_IF_WRITE_DQS_WIDTH,
+					read_test_bgn = 0;
+					read_group < (write_group + 1) *
+					RW_MGR_MEM_IF_READ_DQS_WIDTH /
+					RW_MGR_MEM_IF_WRITE_DQS_WIDTH &&
+					group_failed == 0;
+					read_group++, read_test_bgn +=
+					RW_MGR_MEM_DQ_PER_READ_DQS) {
+					/* Calibrate the VFIFO */
+					if (!((STATIC_CALIB_STEPS) &
+						CALIB_SKIP_VFIFO)) {
+						if (!rw_mgr_mem_calibrate_vfifo
+							(read_group,
+							read_test_bgn)) {
+							group_failed = 1;
+
+							if (!(gbl->
+							phy_debug_mode_flags &
+						PHY_DEBUG_SWEEP_ALL_GROUPS)) {
+								return 0;
+							}
+						}
+					}
+				}
+
+				/* Calibrate the output side */
+				if (group_failed == 0)	{
+					for (rank_bgn = 0, sr = 0; rank_bgn
+						< RW_MGR_MEM_NUMBER_OF_RANKS;
+						rank_bgn +=
+						NUM_RANKS_PER_SHADOW_REG,
+						++sr) {
+						sr_failed = 0;
+						if (!((STATIC_CALIB_STEPS) &
+						CALIB_SKIP_WRITES)) {
+							if ((STATIC_CALIB_STEPS)
+						& CALIB_SKIP_DELAY_SWEEPS) {
+						/* not needed in quick mode! */
+							} else {
+						/*
+						 * Determine if this set of
+						 * ranks should be skipped
+						 * entirely.
+						 */
+					if (!param->skip_shadow_regs[sr]) {
+						if (!rw_mgr_mem_calibrate_writes
+						(rank_bgn, write_group,
+						write_test_bgn)) {
+							sr_failed = 1;
+							if (!(gbl->
+							phy_debug_mode_flags &
+						PHY_DEBUG_SWEEP_ALL_GROUPS)) {
+								return 0;
+									}
+									}
+								}
+							}
+						}
+						if (sr_failed != 0)
+							group_failed = 1;
+					}
+				}
+
+				if (group_failed == 0) {
+					for (read_group = write_group *
+					RW_MGR_MEM_IF_READ_DQS_WIDTH /
+					RW_MGR_MEM_IF_WRITE_DQS_WIDTH,
+					read_test_bgn = 0;
+						read_group < (write_group + 1)
+						* RW_MGR_MEM_IF_READ_DQS_WIDTH
+						/ RW_MGR_MEM_IF_WRITE_DQS_WIDTH &&
+						group_failed == 0;
+						read_group++, read_test_bgn +=
+						RW_MGR_MEM_DQ_PER_READ_DQS) {
+						if (!((STATIC_CALIB_STEPS) &
+							CALIB_SKIP_WRITES)) {
+					if (!rw_mgr_mem_calibrate_vfifo_end
+						(read_group, read_test_bgn)) {
+							group_failed = 1;
+
+						if (!(gbl->phy_debug_mode_flags
+						& PHY_DEBUG_SWEEP_ALL_GROUPS)) {
+								return 0;
+								}
+							}
+						}
+					}
+				}
+
+				if (group_failed != 0)
+					failing_groups++;
+			}
+
+			/*
+			 * USER If there are any failing groups then report
+			 * the failure.
+			 */
+			if (failing_groups != 0)
+				return 0;
+
+			/* Calibrate the LFIFO */
+			if (!((STATIC_CALIB_STEPS) & CALIB_SKIP_LFIFO)) {
+				/*
+				 * If we're skipping groups as part of debug,
+				 * don't calibrate LFIFO.
+				 */
+				if (param->skip_groups == 0) {
+					if (!rw_mgr_mem_calibrate_lfifo())
+						return 0;
+				}
+			}
+		}
+	}
+
+	/*
+	 * Do not remove this line as it makes sure all of our decisions
+	 * have been applied.
+	 */
+	addr = sdr_get_addr(&sdr_scc_mgr->update);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+	return 1;
+}
+
+static uint32_t run_mem_calibrate(void)
+{
+	uint32_t pass;
+	uint32_t debug_info;
+	uint32_t addr;
+
+	debug("%s:%d\n", __func__, __LINE__);
+
+	/* Reset pass/fail status shown on afi_cal_success/fail */
+	addr = sdr_get_addr(&phy_mgr_cfg->cal_status);
+	writel(PHY_MGR_CAL_RESET, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr((u32 *)BASE_MMR);
+	/* stop tracking manger */
+	uint32_t ctrlcfg = readl(SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr((u32 *)BASE_MMR);
+	writel(ctrlcfg & 0xFFBFFFFF, SOCFPGA_SDR_ADDRESS + addr);
+
+	initialize();
+	rw_mgr_mem_initialize();
+
+	pass = mem_calibrate();
+
+	mem_precharge_and_activate();
+	addr = sdr_get_addr(&phy_mgr_cmd->fifo_reset);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	/*
+	 * Handoff:
+	 * Don't return control of the PHY back to AFI when in debug mode.
+	 */
+	if ((gbl->phy_debug_mode_flags & PHY_DEBUG_IN_DEBUG_MODE) == 0) {
+		rw_mgr_mem_handoff();
+		/*
+		 * In Hard PHY this is a 2-bit control:
+		 * 0: AFI Mux Select
+		 * 1: DDIO Mux Select
+		 */
+		addr = sdr_get_addr(&phy_mgr_cfg->mux_sel);
+		writel(0x2, SOCFPGA_SDR_ADDRESS + addr);
+	}
+
+	addr = sdr_get_addr((u32 *)BASE_MMR);
+	writel(ctrlcfg, SOCFPGA_SDR_ADDRESS + addr);
+
+	if (pass) {
+		printf("%s: CALIBRATION PASSED\n", __FILE__);
+
+		gbl->fom_in /= 2;
+		gbl->fom_out /= 2;
+
+		if (gbl->fom_in > 0xff)
+			gbl->fom_in = 0xff;
+
+		if (gbl->fom_out > 0xff)
+			gbl->fom_out = 0xff;
+
+		/* Update the FOM in the register file */
+		debug_info = gbl->fom_in;
+		debug_info |= gbl->fom_out << 8;
+		addr = sdr_get_addr(&sdr_reg_file->fom);
+		writel(debug_info, SOCFPGA_SDR_ADDRESS + addr);
+
+		addr = sdr_get_addr(&phy_mgr_cfg->cal_debug_info);
+		writel(debug_info, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&phy_mgr_cfg->cal_status);
+		writel(PHY_MGR_CAL_SUCCESS, SOCFPGA_SDR_ADDRESS + addr);
+	} else {
+		printf("%s: CALIBRATION FAILED\n", __FILE__);
+
+		debug_info = gbl->error_stage;
+		debug_info |= gbl->error_substage << 8;
+		debug_info |= gbl->error_group << 16;
+
+		addr = sdr_get_addr(&sdr_reg_file->failing_stage);
+		writel(debug_info, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&phy_mgr_cfg->cal_debug_info);
+		writel(debug_info, SOCFPGA_SDR_ADDRESS + addr);
+		addr = sdr_get_addr(&phy_mgr_cfg->cal_status);
+		writel(PHY_MGR_CAL_FAIL, SOCFPGA_SDR_ADDRESS + addr);
+
+		/* Update the failing group/stage in the register file */
+		debug_info = gbl->error_stage;
+		debug_info |= gbl->error_substage << 8;
+		debug_info |= gbl->error_group << 16;
+		addr = sdr_get_addr(&sdr_reg_file->failing_stage);
+		writel(debug_info, SOCFPGA_SDR_ADDRESS + addr);
+	}
+
+	return pass;
+}
+
+static void hc_initialize_rom_data(void)
+{
+	uint32_t i;
+	uint32_t addr;
+
+	addr = sdr_get_addr((u32 *)(RW_MGR_INST_ROM_WRITE));
+	for (i = 0; i < ARRAY_SIZE(inst_rom_init); i++) {
+		uint32_t data = inst_rom_init[i];
+		writel(data, SOCFPGA_SDR_ADDRESS + addr + (i << 2));
+	}
+
+	addr = sdr_get_addr((u32 *)(RW_MGR_AC_ROM_WRITE));
+	for (i = 0; i < ARRAY_SIZE(ac_rom_init); i++) {
+		uint32_t data = ac_rom_init[i];
+		writel(data, SOCFPGA_SDR_ADDRESS + addr + (i << 2));
+	}
+}
+
+static void initialize_reg_file(void)
+{
+	uint32_t addr;
+
+	/* Initialize the register file with the correct data */
+	addr = sdr_get_addr(&sdr_reg_file->signature);
+	writel(REG_FILE_INIT_SEQ_SIGNATURE, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->debug_data_addr);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->cur_stage);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->fom);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->failing_stage);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->debug1);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->debug2);
+	writel(0, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+static void initialize_hps_phy(void)
+{
+	uint32_t reg;
+	uint32_t addr;
+	/*
+	 * Tracking also gets configured here because it's in the
+	 * same register.
+	 */
+	uint32_t trk_sample_count = 7500;
+	uint32_t trk_long_idle_sample_count = (10 << 16) | 100;
+	/*
+	 * Format is number of outer loops in the 16 MSB, sample
+	 * count in 16 LSB.
+	 */
+
+	reg = 0;
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_ACDELAYEN_SET(2);
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_DQDELAYEN_SET(1);
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_DQSDELAYEN_SET(1);
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_DQSLOGICDELAYEN_SET(1);
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_RESETDELAYEN_SET(0);
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_LPDDRDIS_SET(1);
+	/*
+	 * This field selects the intrinsic latency to RDATA_EN/FULL path.
+	 * 00-bypass, 01- add 5 cycles, 10- add 10 cycles, 11- add 15 cycles.
+	 */
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_ADDLATSEL_SET(0);
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_SAMPLECOUNT_19_0_SET(
+		trk_sample_count);
+	addr = sdr_get_addr((u32 *)BASE_MMR);
+	writel(reg, SOCFPGA_SDR_ADDRESS + addr + SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_OFFSET);
+
+	reg = 0;
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_1_SAMPLECOUNT_31_20_SET(
+		trk_sample_count >>
+		SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_SAMPLECOUNT_19_0_WIDTH);
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_1_LONGIDLESAMPLECOUNT_19_0_SET(
+		trk_long_idle_sample_count);
+	writel(reg, SOCFPGA_SDR_ADDRESS + addr + SDR_CTRLGRP_PHYCTRL_PHYCTRL_1_OFFSET);
+
+	reg = 0;
+	reg |= SDR_CTRLGRP_PHYCTRL_PHYCTRL_2_LONGIDLESAMPLECOUNT_31_20_SET(
+		trk_long_idle_sample_count >>
+		SDR_CTRLGRP_PHYCTRL_PHYCTRL_1_LONGIDLESAMPLECOUNT_19_0_WIDTH);
+	writel(reg, SOCFPGA_SDR_ADDRESS + addr + SDR_CTRLGRP_PHYCTRL_PHYCTRL_2_OFFSET);
+}
+
+static void initialize_tracking(void)
+{
+	uint32_t concatenated_longidle = 0x0;
+	uint32_t concatenated_delays = 0x0;
+	uint32_t concatenated_rw_addr = 0x0;
+	uint32_t concatenated_refresh = 0x0;
+	uint32_t trk_sample_count = 7500;
+	uint32_t dtaps_per_ptap;
+	uint32_t tmp_delay;
+	uint32_t addr;
+
+	/*
+	 * compute usable version of value in case we skip full
+	 * computation later
+	 */
+	dtaps_per_ptap = 0;
+	tmp_delay = 0;
+	while (tmp_delay < IO_DELAY_PER_OPA_TAP) {
+		dtaps_per_ptap++;
+		tmp_delay += IO_DELAY_PER_DCHAIN_TAP;
+	}
+	dtaps_per_ptap--;
+
+	concatenated_longidle = concatenated_longidle ^ 10;
+		/*longidle outer loop */
+	concatenated_longidle = concatenated_longidle << 16;
+	concatenated_longidle = concatenated_longidle ^ 100;
+		/*longidle sample count */
+	concatenated_delays = concatenated_delays ^ 243;
+		/* trfc, worst case of 933Mhz 4Gb */
+	concatenated_delays = concatenated_delays << 8;
+	concatenated_delays = concatenated_delays ^ 14;
+		/* trcd, worst case */
+	concatenated_delays = concatenated_delays << 8;
+	concatenated_delays = concatenated_delays ^ 10;
+		/* vfifo wait */
+	concatenated_delays = concatenated_delays << 8;
+	concatenated_delays = concatenated_delays ^ 4;
+		/* mux delay */
+
+	concatenated_rw_addr = concatenated_rw_addr ^ RW_MGR_IDLE;
+	concatenated_rw_addr = concatenated_rw_addr << 8;
+	concatenated_rw_addr = concatenated_rw_addr ^ RW_MGR_ACTIVATE_1;
+	concatenated_rw_addr = concatenated_rw_addr << 8;
+	concatenated_rw_addr = concatenated_rw_addr ^ RW_MGR_SGLE_READ;
+	concatenated_rw_addr = concatenated_rw_addr << 8;
+	concatenated_rw_addr = concatenated_rw_addr ^ RW_MGR_PRECHARGE_ALL;
+
+	concatenated_refresh = concatenated_refresh ^ RW_MGR_REFRESH_ALL;
+	concatenated_refresh = concatenated_refresh << 24;
+	concatenated_refresh = concatenated_refresh ^ 1000; /* trefi */
+
+	/* Initialize the register file with the correct data */
+	addr = sdr_get_addr(&sdr_reg_file->dtaps_per_ptap);
+	writel(dtaps_per_ptap, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->trk_sample_count);
+	writel(trk_sample_count, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->trk_longidle);
+	writel(concatenated_longidle, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->delays);
+	writel(concatenated_delays, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->trk_rw_mgr_addr);
+	writel(concatenated_rw_addr, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->trk_read_dqs_width);
+	writel(RW_MGR_MEM_IF_READ_DQS_WIDTH, SOCFPGA_SDR_ADDRESS + addr);
+
+	addr = sdr_get_addr(&sdr_reg_file->trk_rfsh);
+	writel(concatenated_refresh, SOCFPGA_SDR_ADDRESS + addr);
+}
+
+int sdram_calibration_full(void)
+{
+	struct param_type my_param;
+	struct gbl_type my_gbl;
+	uint32_t pass;
+	uint32_t i;
+
+	param = &my_param;
+	gbl = &my_gbl;
+
+	/* Initialize the debug mode flags */
+	gbl->phy_debug_mode_flags = 0;
+	/* Set the calibration enabled by default */
+	gbl->phy_debug_mode_flags |= PHY_DEBUG_ENABLE_CAL_RPT;
+	/*
+	 * Only sweep all groups (regardless of fail state) by default
+	 * Set enabled read test by default.
+	 */
+#if DISABLE_GUARANTEED_READ
+	gbl->phy_debug_mode_flags |= PHY_DEBUG_DISABLE_GUARANTEED_READ;
+#endif
+	/* Initialize the register file */
+	initialize_reg_file();
+
+	/* Initialize any PHY CSR */
+	initialize_hps_phy();
+
+	scc_mgr_initialize();
+
+	initialize_tracking();
+
+	/* USER Enable all ranks, groups */
+	for (i = 0; i < RW_MGR_MEM_NUMBER_OF_RANKS; i++)
+		param->skip_ranks[i] = 0;
+	for (i = 0; i < NUM_SHADOW_REGS; ++i)
+		param->skip_shadow_regs[i] = 0;
+	param->skip_groups = 0;
+
+	printf("%s: Preparing to start memory calibration\n", __FILE__);
+
+	debug("%s:%d\n", __func__, __LINE__);
+	debug_cond(DLEVEL == 1, "DDR3 FULL_RATE ranks=%lu cs/dimm=%lu dq/dqs=%lu,%lu vg/dqs=%lu,%lu",
+	       (long unsigned int)RW_MGR_MEM_NUMBER_OF_RANKS,
+	       (long unsigned int)RW_MGR_MEM_NUMBER_OF_CS_PER_DIMM,
+	       (long unsigned int)RW_MGR_MEM_DQ_PER_READ_DQS,
+	       (long unsigned int)RW_MGR_MEM_DQ_PER_WRITE_DQS,
+	       (long unsigned int)RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS,
+	       (long unsigned int)RW_MGR_MEM_VIRTUAL_GROUPS_PER_WRITE_DQS);
+	debug_cond(DLEVEL == 1, "dqs=%lu,%lu dq=%lu dm=%lu ptap_delay=%lu dtap_delay=%lu",
+	       (long unsigned int)RW_MGR_MEM_IF_READ_DQS_WIDTH,
+	       (long unsigned int)RW_MGR_MEM_IF_WRITE_DQS_WIDTH,
+	       (long unsigned int)RW_MGR_MEM_DATA_WIDTH,
+	       (long unsigned int)RW_MGR_MEM_DATA_MASK_WIDTH,
+	       (long unsigned int)IO_DELAY_PER_OPA_TAP,
+	       (long unsigned int)IO_DELAY_PER_DCHAIN_TAP);
+	debug_cond(DLEVEL == 1, "dtap_dqsen_delay=%lu, dll=%lu",
+	       (long unsigned int)IO_DELAY_PER_DQS_EN_DCHAIN_TAP,
+	       (long unsigned int)IO_DLL_CHAIN_LENGTH);
+	debug_cond(DLEVEL == 1, "max values: en_p=%lu dqdqs_p=%lu en_d=%lu dqs_in_d=%lu",
+	       (long unsigned int)IO_DQS_EN_PHASE_MAX,
+	       (long unsigned int)IO_DQDQS_OUT_PHASE_MAX,
+	       (long unsigned int)IO_DQS_EN_DELAY_MAX,
+	       (long unsigned int)IO_DQS_IN_DELAY_MAX);
+	debug_cond(DLEVEL == 1, "io_in_d=%lu io_out1_d=%lu io_out2_d=%lu",
+	       (long unsigned int)IO_IO_IN_DELAY_MAX,
+	       (long unsigned int)IO_IO_OUT1_DELAY_MAX,
+	       (long unsigned int)IO_IO_OUT2_DELAY_MAX);
+	debug_cond(DLEVEL == 1, "dqs_in_reserve=%lu dqs_out_reserve=%lu",
+	       (long unsigned int)IO_DQS_IN_RESERVE,
+	       (long unsigned int)IO_DQS_OUT_RESERVE);
+
+	hc_initialize_rom_data();
+
+	/* update info for sims */
+	reg_file_set_stage(CAL_STAGE_NIL);
+	reg_file_set_group(0);
+
+	/*
+	 * Load global needed for those actions that require
+	 * some dynamic calibration support.
+	 */
+	dyn_calib_steps = STATIC_CALIB_STEPS;
+	/*
+	 * Load global to allow dynamic selection of delay loop settings
+	 * based on calibration mode.
+	 */
+	if (!(dyn_calib_steps & CALIB_SKIP_DELAY_LOOPS))
+		skip_delay_mask = 0xff;
+	else
+		skip_delay_mask = 0x0;
+
+	pass = run_mem_calibrate();
+
+	printf("%s: Calibration complete\n", __FILE__);
+	return pass;
+}

drivers/ddr/altera/sequencer.h

@@ -0,0 +1,322 @@
+/*
+ * Copyright Altera Corporation (C) 2012-2015
+ *
+ * SPDX-License-Identifier:    BSD-3-Clause
+ */
+
+#ifndef _SEQUENCER_H_
+#define _SEQUENCER_H_
+
+#define RW_MGR_NUM_DM_PER_WRITE_GROUP (RW_MGR_MEM_DATA_MASK_WIDTH \
+	/ RW_MGR_MEM_IF_WRITE_DQS_WIDTH)
+#define RW_MGR_NUM_TRUE_DM_PER_WRITE_GROUP (RW_MGR_TRUE_MEM_DATA_MASK_WIDTH \
+	/ RW_MGR_MEM_IF_WRITE_DQS_WIDTH)
+
+#define RW_MGR_NUM_DQS_PER_WRITE_GROUP (RW_MGR_MEM_IF_READ_DQS_WIDTH \
+	/ RW_MGR_MEM_IF_WRITE_DQS_WIDTH)
+#define NUM_RANKS_PER_SHADOW_REG (RW_MGR_MEM_NUMBER_OF_RANKS / NUM_SHADOW_REGS)
+
+#define RW_MGR_RUN_SINGLE_GROUP	(BASE_RW_MGR)
+#define RW_MGR_RUN_ALL_GROUPS	(BASE_RW_MGR + 0x0400)
+
+#define RW_MGR_DI_BASE		(BASE_RW_MGR + 0x0020)
+
+#define RW_MGR_MEM_NUMBER_OF_RANKS	1
+#define NUM_SHADOW_REGS			1
+
+#define RW_MGR_RESET_READ_DATAPATH	(BASE_RW_MGR + 0x1000)
+#define RW_MGR_SET_CS_AND_ODT_MASK	(BASE_RW_MGR + 0x1400)
+
+#define RW_MGR_RANK_NONE		0xFF
+#define RW_MGR_RANK_ALL			0x00
+
+#define RW_MGR_ODT_MODE_OFF		0
+#define RW_MGR_ODT_MODE_READ_WRITE	1
+
+#define NUM_CALIB_REPEAT		1
+
+#define NUM_READ_TESTS			7
+#define NUM_READ_PB_TESTS		7
+#define NUM_WRITE_TESTS			15
+#define NUM_WRITE_PB_TESTS		31
+
+#define PASS_ALL_BITS			1
+#define PASS_ONE_BIT			0
+
+/* calibration stages */
+#define CAL_STAGE_NIL			0
+#define CAL_STAGE_VFIFO			1
+#define CAL_STAGE_WLEVEL		2
+#define CAL_STAGE_LFIFO			3
+#define CAL_STAGE_WRITES		4
+#define CAL_STAGE_FULLTEST		5
+#define CAL_STAGE_REFRESH		6
+#define CAL_STAGE_CAL_SKIPPED		7
+#define CAL_STAGE_CAL_ABORTED		8
+#define CAL_STAGE_VFIFO_AFTER_WRITES	9
+
+/* calibration substages */
+#define CAL_SUBSTAGE_NIL		0
+#define CAL_SUBSTAGE_GUARANTEED_READ	1
+#define CAL_SUBSTAGE_DQS_EN_PHASE	2
+#define CAL_SUBSTAGE_VFIFO_CENTER	3
+#define CAL_SUBSTAGE_WORKING_DELAY	1
+#define CAL_SUBSTAGE_LAST_WORKING_DELAY	2
+#define CAL_SUBSTAGE_WLEVEL_COPY	3
+#define CAL_SUBSTAGE_WRITES_CENTER	1
+#define CAL_SUBSTAGE_READ_LATENCY	1
+#define CAL_SUBSTAGE_REFRESH		1
+
+#define MAX_RANKS			(RW_MGR_MEM_NUMBER_OF_RANKS)
+#define MAX_DQS				(RW_MGR_MEM_IF_WRITE_DQS_WIDTH > \
+					RW_MGR_MEM_IF_READ_DQS_WIDTH ? \
+					RW_MGR_MEM_IF_WRITE_DQS_WIDTH : \
+					RW_MGR_MEM_IF_READ_DQS_WIDTH)
+#define MAX_DQ				(RW_MGR_MEM_DATA_WIDTH)
+#define MAX_DM				(RW_MGR_MEM_DATA_MASK_WIDTH)
+
+/* length of VFIFO, from SW_MACROS */
+#define VFIFO_SIZE			(READ_VALID_FIFO_SIZE)
+
+/* MarkW: how should these base addresses be done for A-V? */
+#define BASE_PTR_MGR			0x00040000
+#define BASE_SCC_MGR			0x00058000
+#define BASE_REG_FILE			0x00070000
+#define BASE_TIMER			0x00078000
+#define BASE_PHY_MGR			0x00088000
+#define BASE_RW_MGR			0x00090000
+#define BASE_DATA_MGR			0x00098000
+#define BASE_MMR			0x000C0000
+#define BASE_TRK_MGR			0x000D0000
+
+#define SCC_MGR_GROUP_COUNTER			(BASE_SCC_MGR + 0x0000)
+#define SCC_MGR_DQS_IN_DELAY			(BASE_SCC_MGR + 0x0100)
+#define SCC_MGR_DQS_EN_PHASE			(BASE_SCC_MGR + 0x0200)
+#define SCC_MGR_DQS_EN_DELAY			(BASE_SCC_MGR + 0x0300)
+#define SCC_MGR_DQDQS_OUT_PHASE			(BASE_SCC_MGR + 0x0400)
+#define SCC_MGR_OCT_OUT1_DELAY			(BASE_SCC_MGR + 0x0500)
+#define SCC_MGR_IO_OUT1_DELAY			(BASE_SCC_MGR + 0x0700)
+#define SCC_MGR_IO_IN_DELAY			(BASE_SCC_MGR + 0x0900)
+
+/* HHP-HPS-specific versions of some commands */
+#define SCC_MGR_DQS_EN_DELAY_GATE		(BASE_SCC_MGR + 0x0600)
+#define SCC_MGR_IO_OE_DELAY			(BASE_SCC_MGR + 0x0800)
+#define SCC_MGR_HHP_GLOBALS			(BASE_SCC_MGR + 0x0A00)
+#define SCC_MGR_HHP_RFILE			(BASE_SCC_MGR + 0x0B00)
+#define SCC_MGR_AFI_CAL_INIT			(BASE_SCC_MGR + 0x0D00)
+
+#define SDR_PHYGRP_SCCGRP_ADDRESS		0x0
+#define SDR_PHYGRP_PHYMGRGRP_ADDRESS		0x1000
+#define SDR_PHYGRP_RWMGRGRP_ADDRESS		0x2000
+#define SDR_PHYGRP_DATAMGRGRP_ADDRESS		0x4000
+#define SDR_PHYGRP_REGFILEGRP_ADDRESS		0x4800
+
+#define SDR_CTRLGRP_PHYCTRL_PHYCTRL_0_OFFSET 0x150
+#define SDR_CTRLGRP_PHYCTRL_PHYCTRL_1_OFFSET 0x154
+#define SDR_CTRLGRP_PHYCTRL_PHYCTRL_2_OFFSET 0x158
+
+#define PHY_MGR_CAL_RESET		(0)
+#define PHY_MGR_CAL_SUCCESS		(1)
+#define PHY_MGR_CAL_FAIL		(2)
+
+#define CALIB_SKIP_DELAY_LOOPS		(1 << 0)
+#define CALIB_SKIP_ALL_BITS_CHK		(1 << 1)
+#define CALIB_SKIP_DELAY_SWEEPS		(1 << 2)
+#define CALIB_SKIP_VFIFO		(1 << 3)
+#define CALIB_SKIP_LFIFO		(1 << 4)
+#define CALIB_SKIP_WLEVEL		(1 << 5)
+#define CALIB_SKIP_WRITES		(1 << 6)
+#define CALIB_SKIP_FULL_TEST		(1 << 7)
+#define CALIB_SKIP_ALL			(CALIB_SKIP_VFIFO | \
+				CALIB_SKIP_LFIFO | CALIB_SKIP_WLEVEL | \
+				CALIB_SKIP_WRITES | CALIB_SKIP_FULL_TEST)
+#define CALIB_IN_RTL_SIM			(1 << 8)
+
+/* Scan chain manager command addresses */
+#define READ_SCC_OCT_OUT2_DELAY			0
+#define READ_SCC_DQ_OUT2_DELAY			0
+#define READ_SCC_DQS_IO_OUT2_DELAY		0
+#define READ_SCC_DM_IO_OUT2_DELAY		0
+
+/* HHP-HPS-specific values */
+#define SCC_MGR_HHP_EXTRAS_OFFSET			0
+#define SCC_MGR_HHP_DQSE_MAP_OFFSET			1
+
+/* PHY Debug mode flag constants */
+#define PHY_DEBUG_IN_DEBUG_MODE 0x00000001
+#define PHY_DEBUG_ENABLE_CAL_RPT 0x00000002
+#define PHY_DEBUG_ENABLE_MARGIN_RPT 0x00000004
+#define PHY_DEBUG_SWEEP_ALL_GROUPS 0x00000008
+#define PHY_DEBUG_DISABLE_GUARANTEED_READ 0x00000010
+#define PHY_DEBUG_ENABLE_NON_DESTRUCTIVE_CALIBRATION 0x00000020
+
+/* Init and Reset delay constants - Only use if defined by sequencer_defines.h,
+ * otherwise, revert to defaults
+ * Default for Tinit = (0+1) * ((202+1) * (2 * 131 + 1) + 1) = 53532 =
+ * 200.75us @ 266MHz
+ */
+#ifdef TINIT_CNTR0_VAL
+#define SEQ_TINIT_CNTR0_VAL TINIT_CNTR0_VAL
+#else
+#define SEQ_TINIT_CNTR0_VAL 0
+#endif
+
+#ifdef TINIT_CNTR1_VAL
+#define SEQ_TINIT_CNTR1_VAL TINIT_CNTR1_VAL
+#else
+#define SEQ_TINIT_CNTR1_VAL 202
+#endif
+
+#ifdef TINIT_CNTR2_VAL
+#define SEQ_TINIT_CNTR2_VAL TINIT_CNTR2_VAL
+#else
+#define SEQ_TINIT_CNTR2_VAL 131
+#endif
+
+
+/* Default for Treset = (2+1) * ((252+1) * (2 * 131 + 1) + 1) = 133563 =
+ * 500.86us @ 266MHz
+ */
+#ifdef TRESET_CNTR0_VAL
+#define SEQ_TRESET_CNTR0_VAL TRESET_CNTR0_VAL
+#else
+#define SEQ_TRESET_CNTR0_VAL 2
+#endif
+
+#ifdef TRESET_CNTR1_VAL
+#define SEQ_TRESET_CNTR1_VAL TRESET_CNTR1_VAL
+#else
+#define SEQ_TRESET_CNTR1_VAL 252
+#endif
+
+#ifdef TRESET_CNTR2_VAL
+#define SEQ_TRESET_CNTR2_VAL TRESET_CNTR2_VAL
+#else
+#define SEQ_TRESET_CNTR2_VAL 131
+#endif
+
+#define RW_MGR_INST_ROM_WRITE BASE_RW_MGR + 0x1800
+#define RW_MGR_AC_ROM_WRITE BASE_RW_MGR + 0x1C00
+
+struct socfpga_sdr_rw_load_manager {
+	u32	load_cntr0;
+	u32	load_cntr1;
+	u32	load_cntr2;
+	u32	load_cntr3;
+};
+
+struct socfpga_sdr_rw_load_jump_manager {
+	u32	load_jump_add0;
+	u32	load_jump_add1;
+	u32	load_jump_add2;
+	u32	load_jump_add3;
+};
+
+struct socfpga_sdr_reg_file {
+	u32 signature;
+	u32 debug_data_addr;
+	u32 cur_stage;
+	u32 fom;
+	u32 failing_stage;
+	u32 debug1;
+	u32 debug2;
+	u32 dtaps_per_ptap;
+	u32 trk_sample_count;
+	u32 trk_longidle;
+	u32 delays;
+	u32 trk_rw_mgr_addr;
+	u32 trk_read_dqs_width;
+	u32 trk_rfsh;
+};
+
+/* parameter variable holder */
+struct param_type {
+	uint32_t dm_correct_mask;
+	uint32_t read_correct_mask;
+	uint32_t read_correct_mask_vg;
+	uint32_t write_correct_mask;
+	uint32_t write_correct_mask_vg;
+
+	/* set a particular entry to 1 if we need to skip a particular rank */
+
+	uint32_t skip_ranks[MAX_RANKS];
+
+	/* set a particular entry to 1 if we need to skip a particular group */
+
+	uint32_t skip_groups;
+
+	/* set a particular entry to 1 if the shadow register
+	(which represents a set of ranks) needs to be skipped */
+
+	uint32_t skip_shadow_regs[NUM_SHADOW_REGS];
+
+};
+
+
+/* global variable holder */
+struct gbl_type {
+	uint32_t phy_debug_mode_flags;
+
+	/* current read latency */
+
+	uint32_t curr_read_lat;
+
+	/* current write latency */
+
+	uint32_t curr_write_lat;
+
+	/* error code */
+
+	uint32_t error_substage;
+	uint32_t error_stage;
+	uint32_t error_group;
+
+	/* figure-of-merit in, figure-of-merit out */
+
+	uint32_t fom_in;
+	uint32_t fom_out;
+
+	/*USER Number of RW Mgr NOP cycles between
+	write command and write data */
+	uint32_t rw_wl_nop_cycles;
+};
+
+struct socfpga_sdr_scc_mgr {
+	u32	dqs_ena;
+	u32	dqs_io_ena;
+	u32	dq_ena;
+	u32	dm_ena;
+	u32	__padding1[4];
+	u32	update;
+	u32	__padding2[7];
+	u32	active_rank;
+};
+
+/* PHY manager configuration registers. */
+struct socfpga_phy_mgr_cfg {
+	u32	phy_rlat;
+	u32	reset_mem_stbl;
+	u32	mux_sel;
+	u32	cal_status;
+	u32	cal_debug_info;
+	u32	vfifo_rd_en_ovrd;
+	u32	afi_wlat;
+	u32	afi_rlat;
+};
+
+/* PHY manager command addresses. */
+struct socfpga_phy_mgr_cmd {
+	u32	inc_vfifo_fr;
+	u32	inc_vfifo_hard_phy;
+	u32	fifo_reset;
+	u32	inc_vfifo_fr_hr;
+	u32	inc_vfifo_qr;
+};
+
+struct socfpga_data_mgr {
+	u32	__padding1;
+	u32	t_wl_add;
+	u32	mem_t_add;
+	u32	t_rl_add;
+};
+#endif /* _SEQUENCER_H_ */

drivers/ddr/altera/sequencer_auto.h

@@ -0,0 +1,128 @@
+/*
+ * Copyright Altera Corporation (C) 2012-2015
+ *
+ * SPDX-License-Identifier:    BSD-3-Clause
+ */
+
+
+#define RW_MGR_READ_B2B_WAIT2 0x6A
+#define RW_MGR_LFSR_WR_RD_BANK_0_WAIT 0x31
+#define RW_MGR_REFRESH_ALL 0x14
+#define RW_MGR_ZQCL 0x06
+#define RW_MGR_LFSR_WR_RD_BANK_0_NOP 0x22
+#define RW_MGR_LFSR_WR_RD_BANK_0_DQS 0x23
+#define RW_MGR_ACTIVATE_0_AND_1 0x0D
+#define RW_MGR_MRS2_MIRR 0x0A
+#define RW_MGR_INIT_RESET_0_CKE_0 0x6E
+#define RW_MGR_LFSR_WR_RD_DM_BANK_0_WAIT 0x45
+#define RW_MGR_ACTIVATE_1 0x0F
+#define RW_MGR_MRS2 0x04
+#define RW_MGR_LFSR_WR_RD_DM_BANK_0_WL_1 0x34
+#define RW_MGR_MRS1 0x03
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define RW_MGR_IDLE_LOOP1 0x7A
+#else
+#define RW_MGR_IDLE_LOOP1 0x7C
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define RW_MGR_GUARANTEED_WRITE_WAIT2 0x18
+#define RW_MGR_MRS3 0x05
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define RW_MGR_IDLE_LOOP2 0x79
+#else
+#define RW_MGR_IDLE_LOOP2 0x7B
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define RW_MGR_GUARANTEED_WRITE_WAIT1 0x1E
+#define RW_MGR_LFSR_WR_RD_BANK_0_DATA 0x24
+#define RW_MGR_GUARANTEED_WRITE_WAIT3 0x1C
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define RW_MGR_RDIMM_CMD 0x78
+#else
+#define RW_MGR_RDIMM_CMD 0x7A
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define RW_MGR_LFSR_WR_RD_DM_BANK_0_NOP 0x36
+#define RW_MGR_GUARANTEED_WRITE_WAIT0 0x1A
+#define RW_MGR_LFSR_WR_RD_DM_BANK_0_DATA 0x38
+#define RW_MGR_GUARANTEED_READ_CONT 0x53
+#define RW_MGR_MRS3_MIRR 0x0B
+#define RW_MGR_IDLE 0x00
+#define RW_MGR_READ_B2B 0x58
+#define RW_MGR_INIT_RESET_0_CKE_0_inloop 0x6F
+#define RW_MGR_LFSR_WR_RD_DM_BANK_0_DQS 0x37
+#define RW_MGR_GUARANTEED_WRITE 0x17
+#define RW_MGR_PRECHARGE_ALL 0x12
+#define RW_MGR_INIT_RESET_1_CKE_0_inloop_1 0x74
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define RW_MGR_SGLE_READ 0x7C
+#else
+#define RW_MGR_SGLE_READ 0x7E
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define RW_MGR_MRS0_USER_MIRR 0x0C
+#define RW_MGR_RETURN 0x01
+#define RW_MGR_LFSR_WR_RD_DM_BANK_0 0x35
+#define RW_MGR_MRS0_USER 0x07
+#define RW_MGR_GUARANTEED_READ 0x4B
+#define RW_MGR_MRS0_DLL_RESET_MIRR 0x08
+#define RW_MGR_INIT_RESET_1_CKE_0 0x73
+#define RW_MGR_ACTIVATE_0_AND_1_WAIT2 0x10
+#define RW_MGR_LFSR_WR_RD_BANK_0_WL_1 0x20
+#define RW_MGR_MRS0_DLL_RESET 0x02
+#define RW_MGR_ACTIVATE_0_AND_1_WAIT1 0x0E
+#define RW_MGR_LFSR_WR_RD_BANK_0 0x21
+#define RW_MGR_CLEAR_DQS_ENABLE 0x48
+#define RW_MGR_MRS1_MIRR 0x09
+#define RW_MGR_READ_B2B_WAIT1 0x60
+#define RW_MGR_CONTENT_READ_B2B_WAIT2 0x00C680
+#define RW_MGR_CONTENT_LFSR_WR_RD_BANK_0_WAIT 0x00A680
+#define RW_MGR_CONTENT_REFRESH_ALL 0x000980
+#define RW_MGR_CONTENT_ZQCL 0x008380
+#define RW_MGR_CONTENT_LFSR_WR_RD_BANK_0_NOP 0x00E700
+#define RW_MGR_CONTENT_LFSR_WR_RD_BANK_0_DQS 0x000C00
+#define RW_MGR_CONTENT_ACTIVATE_0_AND_1 0x000800
+#define RW_MGR_CONTENT_MRS2_MIRR 0x008580
+#define RW_MGR_CONTENT_INIT_RESET_0_CKE_0 0x000000
+#define RW_MGR_CONTENT_LFSR_WR_RD_DM_BANK_0_WAIT 0x00A680
+#define RW_MGR_CONTENT_ACTIVATE_1 0x000880
+#define RW_MGR_CONTENT_MRS2 0x008280
+#define RW_MGR_CONTENT_LFSR_WR_RD_DM_BANK_0_WL_1 0x00CE00
+#define RW_MGR_CONTENT_MRS1 0x008200
+#define RW_MGR_CONTENT_IDLE_LOOP1 0x00A680
+#define RW_MGR_CONTENT_GUARANTEED_WRITE_WAIT2 0x00CCE8
+#define RW_MGR_CONTENT_MRS3 0x008300
+#define RW_MGR_CONTENT_IDLE_LOOP2 0x008680
+#define RW_MGR_CONTENT_GUARANTEED_WRITE_WAIT1 0x00AC88
+#define RW_MGR_CONTENT_LFSR_WR_RD_BANK_0_DATA 0x020CE0
+#define RW_MGR_CONTENT_GUARANTEED_WRITE_WAIT3 0x00EC88
+#define RW_MGR_CONTENT_RDIMM_CMD 0x009180
+#define RW_MGR_CONTENT_LFSR_WR_RD_DM_BANK_0_NOP 0x00E700
+#define RW_MGR_CONTENT_GUARANTEED_WRITE_WAIT0 0x008CE8
+#define RW_MGR_CONTENT_LFSR_WR_RD_DM_BANK_0_DATA 0x030CE0
+#define RW_MGR_CONTENT_GUARANTEED_READ_CONT 0x001168
+#define RW_MGR_CONTENT_MRS3_MIRR 0x008600
+#define RW_MGR_CONTENT_IDLE 0x080000
+#define RW_MGR_CONTENT_READ_B2B 0x040E88
+#define RW_MGR_CONTENT_INIT_RESET_0_CKE_0_inloop 0x000000
+#define RW_MGR_CONTENT_LFSR_WR_RD_DM_BANK_0_DQS 0x000C00
+#define RW_MGR_CONTENT_GUARANTEED_WRITE 0x000B68
+#define RW_MGR_CONTENT_PRECHARGE_ALL 0x000900
+#define RW_MGR_CONTENT_INIT_RESET_1_CKE_0_inloop_1 0x000080
+#define RW_MGR_CONTENT_SGLE_READ 0x040F08
+#define RW_MGR_CONTENT_MRS0_USER_MIRR 0x008400
+#define RW_MGR_CONTENT_RETURN 0x080680
+#define RW_MGR_CONTENT_LFSR_WR_RD_DM_BANK_0 0x00CD80
+#define RW_MGR_CONTENT_MRS0_USER 0x008100
+#define RW_MGR_CONTENT_GUARANTEED_READ 0x001168
+#define RW_MGR_CONTENT_MRS0_DLL_RESET_MIRR 0x008480
+#define RW_MGR_CONTENT_INIT_RESET_1_CKE_0 0x000080
+#define RW_MGR_CONTENT_ACTIVATE_0_AND_1_WAIT2 0x00A680
+#define RW_MGR_CONTENT_LFSR_WR_RD_BANK_0_WL_1 0x00CE00
+#define RW_MGR_CONTENT_MRS0_DLL_RESET 0x008180
+#define RW_MGR_CONTENT_ACTIVATE_0_AND_1_WAIT1 0x008680
+#define RW_MGR_CONTENT_LFSR_WR_RD_BANK_0 0x00CD80
+#define RW_MGR_CONTENT_CLEAR_DQS_ENABLE 0x001158
+#define RW_MGR_CONTENT_MRS1_MIRR 0x008500
+#define RW_MGR_CONTENT_READ_B2B_WAIT1 0x00A680
+

drivers/ddr/altera/sequencer_auto_ac_init.h

@@ -0,0 +1,84 @@
+/*
+ * Copyright Altera Corporation (C) 2012-2015
+ *
+ * SPDX-License-Identifier:    BSD-3-Clause
+ */
+
+const uint32_t ac_rom_init[] = {
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+	0x20700000,
+	0x20780000,
+	0x10080831,
+	0x10080930,
+	0x10090004,
+	0x100a0008,
+	0x100b0000,
+	0x10380400,
+	0x10080849,
+	0x100808c8,
+	0x100a0004,
+	0x10090010,
+	0x100b0000,
+	0x30780000,
+	0x38780000,
+	0x30780000,
+	0x10680000,
+	0x106b0000,
+	0x10280400,
+	0x10480000,
+	0x1c980000,
+	0x1c9b0000,
+	0x1c980008,
+	0x1c9b0008,
+	0x38f80000,
+	0x3cf80000,
+	0x38780000,
+	0x18180000,
+	0x18980000,
+	0x13580000,
+	0x135b0000,
+	0x13580008,
+	0x135b0008,
+	0x33780000,
+	0x10580008,
+	0x10780000
+#else
+	0x20700000,
+	0x20780000,
+	0x10080431,
+	0x10080530,
+	0x10090004,
+	0x100a0008,
+	0x100b0000,
+	0x10380400,
+	0x10080449,
+	0x100804c8,
+	0x100a0004,
+	0x10090010,
+	0x100b0000,
+	0x30780000,
+	0x38780000,
+	0x30780000,
+	0x10680000,
+	0x106b0000,
+	0x10280400,
+	0x10480000,
+	0x1c980000,
+	0x1c9b0000,
+	0x1c980008,
+	0x1c9b0008,
+	0x38f80000,
+	0x3cf80000,
+	0x38780000,
+	0x18180000,
+	0x18980000,
+	0x13580000,
+	0x135b0000,
+	0x13580008,
+	0x135b0008,
+	0x33780000,
+	0x10580008,
+	0x10780000
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+};

drivers/ddr/altera/sequencer_auto_inst_init.h

@@ -0,0 +1,268 @@
+/*
+ * Copyright Altera Corporation (C) 2012-2015
+ *
+ * SPDX-License-Identifier:    BSD-3-Clause
+ */
+
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+const u32 inst_rom_init[] = {
+	0x80000,
+	0x80680,
+	0x8180,
+	0x8200,
+	0x8280,
+	0x8300,
+	0x8380,
+	0x8100,
+	0x8480,
+	0x8500,
+	0x8580,
+	0x8600,
+	0x8400,
+	0x800,
+	0x8680,
+	0x880,
+	0xa680,
+	0x80680,
+	0x900,
+	0x80680,
+	0x980,
+	0x8680,
+	0x80680,
+	0xb68,
+	0xcce8,
+	0xae8,
+	0x8ce8,
+	0xb88,
+	0xec88,
+	0xa08,
+	0xac88,
+	0x80680,
+	0xce00,
+	0xcd80,
+	0xe700,
+	0xc00,
+	0x20ce0,
+	0x20ce0,
+	0x20ce0,
+	0x20ce0,
+	0xd00,
+	0x680,
+	0x680,
+	0x680,
+	0x680,
+	0x60e80,
+	0x61080,
+	0x61080,
+	0x61080,
+	0xa680,
+	0x8680,
+	0x80680,
+	0xce00,
+	0xcd80,
+	0xe700,
+	0xc00,
+	0x30ce0,
+	0x30ce0,
+	0x30ce0,
+	0x30ce0,
+	0xd00,
+	0x680,
+	0x680,
+	0x680,
+	0x680,
+	0x70e80,
+	0x71080,
+	0x71080,
+	0x71080,
+	0xa680,
+	0x8680,
+	0x80680,
+	0x1158,
+	0x6d8,
+	0x80680,
+	0x1168,
+	0x7e8,
+	0x7e8,
+	0x87e8,
+	0x40fe8,
+	0x410e8,
+	0x410e8,
+	0x410e8,
+	0x1168,
+	0x7e8,
+	0x7e8,
+	0xa7e8,
+	0x80680,
+	0x40e88,
+	0x41088,
+	0x41088,
+	0x41088,
+	0x40f68,
+	0x410e8,
+	0x410e8,
+	0x410e8,
+	0xa680,
+	0x40fe8,
+	0x410e8,
+	0x410e8,
+	0x410e8,
+	0x41008,
+	0x41088,
+	0x41088,
+	0x41088,
+	0x1100,
+	0xc680,
+	0x8680,
+	0xe680,
+	0x80680,
+	0x0,
+	0x8000,
+	0xa000,
+	0xc000,
+	0x80000,
+	0x80,
+	0x8080,
+	0xa080,
+	0xc080,
+	0x80080,
+	0x9180,
+	0x8680,
+	0xa680,
+	0x80680,
+	0x40f08,
+	0x80680
+};
+#else
+const u32 inst_rom_init[] = {
+	0x80000,
+	0x80680,
+	0x8180,
+	0x8200,
+	0x8280,
+	0x8300,
+	0x8380,
+	0x8100,
+	0x8480,
+	0x8500,
+	0x8580,
+	0x8600,
+	0x8400,
+	0x800,
+	0x8680,
+	0x880,
+	0xa680,
+	0x80680,
+	0x900,
+	0x80680,
+	0x980,
+	0x8680,
+	0x80680,
+	0xb68,
+	0xcce8,
+	0xae8,
+	0x8ce8,
+	0xb88,
+	0xec88,
+	0xa08,
+	0xac88,
+	0x80680,
+	0xce00,
+	0xcd80,
+	0xe700,
+	0xc00,
+	0x20ce0,
+	0x20ce0,
+	0x20ce0,
+	0x20ce0,
+	0xd00,
+	0x680,
+	0x680,
+	0x680,
+	0x680,
+	0x60e80,
+	0x61080,
+	0x61080,
+	0x61080,
+	0xa680,
+	0x8680,
+	0x80680,
+	0xce00,
+	0xcd80,
+	0xe700,
+	0xc00,
+	0x30ce0,
+	0x30ce0,
+	0x30ce0,
+	0x30ce0,
+	0xd00,
+	0x680,
+	0x680,
+	0x680,
+	0x680,
+	0x70e80,
+	0x71080,
+	0x71080,
+	0x71080,
+	0xa680,
+	0x8680,
+	0x80680,
+	0x1158,
+	0x6d8,
+	0x80680,
+	0x1168,
+	0x7e8,
+	0x7e8,
+	0x87e8,
+	0x40fe8,
+	0x410e8,
+	0x410e8,
+	0x410e8,
+	0x1168,
+	0x7e8,
+	0x7e8,
+	0xa7e8,
+	0x80680,
+	0x40e88,
+	0x41088,
+	0x41088,
+	0x41088,
+	0x40f68,
+	0x410e8,
+	0x410e8,
+	0x410e8,
+	0xa680,
+	0x40fe8,
+	0x410e8,
+	0x410e8,
+	0x410e8,
+	0x41008,
+	0x41088,
+	0x41088,
+	0x41088,
+	0x1100,
+	0xc680,
+	0x8680,
+	0xe680,
+	0x80680,
+	0x0,
+	0x0,
+	0xa000,
+	0x8000,
+	0x80000,
+	0x80,
+	0x80,
+	0x80,
+	0x80,
+	0xa080,
+	0x8080,
+	0x80080,
+	0x9180,
+	0x8680,
+	0xa680,
+	0x80680,
+	0x40f08,
+	0x80680
+};
+#endif /* CONFIG_SOCFPGA_ARRIA5 */

drivers/ddr/altera/sequencer_defines.h

@@ -0,0 +1,121 @@
+/*
+ * Copyright Altera Corporation (C) 2012-2015
+ *
+ * SPDX-License-Identifier:    BSD-3-Clause
+ */
+
+#ifndef _SEQUENCER_DEFINES_H_
+#define _SEQUENCER_DEFINES_H_
+
+#define AC_ROM_MR1_MIRR 0000000000100
+#define AC_ROM_MR1_OCD_ENABLE
+#define AC_ROM_MR2_MIRR 0000000010000
+#define AC_ROM_MR3_MIRR 0000000000000
+#define AC_ROM_MR0_CALIB
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define AC_ROM_MR0_DLL_RESET_MIRR 0100011001000
+#define AC_ROM_MR0_DLL_RESET 0100100110000
+#define AC_ROM_MR0_MIRR 0100001001001
+#define AC_ROM_MR0 0100000110001
+#else
+#define AC_ROM_MR0_DLL_RESET_MIRR 0010011001000
+#define AC_ROM_MR0_DLL_RESET 0010100110000
+#define AC_ROM_MR0_MIRR 0010001001001
+#define AC_ROM_MR0 0010000110001
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define AC_ROM_MR1 0000000000100
+#define AC_ROM_MR2 0000000001000
+#define AC_ROM_MR3 0000000000000
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define AFI_CLK_FREQ 534
+#else
+#define AFI_CLK_FREQ 401
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define AFI_RATE_RATIO 1
+#define AVL_CLK_FREQ 67
+#define BFM_MODE 0
+#define BURST2 0
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define CALIB_LFIFO_OFFSET 8
+#define CALIB_VFIFO_OFFSET 6
+#else
+#define CALIB_LFIFO_OFFSET 7
+#define CALIB_VFIFO_OFFSET 5
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define ENABLE_EXPORT_SEQ_DEBUG_BRIDGE 0
+#define ENABLE_SUPER_QUICK_CALIBRATION 0
+#define GUARANTEED_READ_BRINGUP_TEST 0
+#define HARD_PHY 1
+#define HARD_VFIFO 1
+#define HPS_HW 1
+#define HR_DDIO_OUT_HAS_THREE_REGS 0
+#define IO_DELAY_PER_DCHAIN_TAP 25
+#define IO_DELAY_PER_DQS_EN_DCHAIN_TAP 25
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define IO_DELAY_PER_OPA_TAP 234
+#else
+#define IO_DELAY_PER_OPA_TAP 312
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define IO_DLL_CHAIN_LENGTH 8
+#define IO_DM_OUT_RESERVE 0
+#define IO_DQDQS_OUT_PHASE_MAX 0
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define IO_DQS_EN_DELAY_MAX 15
+#define IO_DQS_EN_DELAY_OFFSET 16
+#else
+#define IO_DQS_EN_DELAY_MAX 31
+#define IO_DQS_EN_DELAY_OFFSET 0
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define IO_DQS_EN_PHASE_MAX 7
+#define IO_DQS_IN_DELAY_MAX 31
+#define IO_DQS_IN_RESERVE 4
+#define IO_DQS_OUT_RESERVE 6
+#define IO_DQ_OUT_RESERVE 0
+#define IO_IO_IN_DELAY_MAX 31
+#define IO_IO_OUT1_DELAY_MAX 31
+#define IO_IO_OUT2_DELAY_MAX 0
+#define IO_SHIFT_DQS_EN_WHEN_SHIFT_DQS 0
+#define MARGIN_VARIATION_TEST 0
+#define MAX_LATENCY_COUNT_WIDTH 5
+#define MEM_ADDR_WIDTH 13
+#define READ_VALID_FIFO_SIZE 16
+#ifdef CONFIG_SOCFPGA_ARRIA5
+/* The if..else... is not required if generated by tools */
+#define REG_FILE_INIT_SEQ_SIGNATURE 0x5555048c
+#else
+#define REG_FILE_INIT_SEQ_SIGNATURE 0x55550483
+#endif /* CONFIG_SOCFPGA_ARRIA5 */
+#define RW_MGR_MEM_ADDRESS_MIRRORING 0
+#define RW_MGR_MEM_ADDRESS_WIDTH 15
+#define RW_MGR_MEM_BANK_WIDTH 3
+#define RW_MGR_MEM_CHIP_SELECT_WIDTH 1
+#define RW_MGR_MEM_CLK_EN_WIDTH 1
+#define RW_MGR_MEM_CONTROL_WIDTH 1
+#define RW_MGR_MEM_DATA_MASK_WIDTH 5
+#define RW_MGR_MEM_DATA_WIDTH 40
+#define RW_MGR_MEM_DQ_PER_READ_DQS 8
+#define RW_MGR_MEM_DQ_PER_WRITE_DQS 8
+#define RW_MGR_MEM_IF_READ_DQS_WIDTH 5
+#define RW_MGR_MEM_IF_WRITE_DQS_WIDTH 5
+#define RW_MGR_MEM_NUMBER_OF_CS_PER_DIMM 1
+#define RW_MGR_MEM_ODT_WIDTH 1
+#define RW_MGR_MEM_VIRTUAL_GROUPS_PER_READ_DQS 1
+#define RW_MGR_MEM_VIRTUAL_GROUPS_PER_WRITE_DQS 1
+#define RW_MGR_MR0_BL 1
+#define RW_MGR_MR0_CAS_LATENCY 3
+#define RW_MGR_TRUE_MEM_DATA_MASK_WIDTH 5
+#define RW_MGR_WRITE_TO_DEBUG_READ 1.0
+#define SKEW_CALIBRATION 0
+#define TINIT_CNTR1_VAL 32
+#define TINIT_CNTR2_VAL 32
+#define TINIT_CNTR0_VAL 132
+#define TRESET_CNTR1_VAL 99
+#define TRESET_CNTR2_VAL 10
+#define TRESET_CNTR0_VAL 132
+
+#endif /* _SEQUENCER_DEFINES_H_ */