sunxi: DRAM initialisation for sun9i

This adds DRAM initialisation code for sun9i, which calculates the
appropriate timings based on timing information for the supplied
DDR3 bin and the clock speeds used.

With this DRAM setup, we have verified DDR3 clocks of up to 792MHz
(i.e. DDR3-1600) on the A80-Q7 using a dual-channel configuration.

[wens@csie.org: Moved dram_sun9i.c to arch/arm/mach-sunxi/; style cleanup]
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
[hdegoede@redhat.com: Drop some huge non-documenting #if 0 ... #endif blocks]
[hdegoede@redhat.com: Fix checkpatch warnings]
Signed-off-by: Hans de Goede <hdegoede@redhat.com>

7 files changed, 1273 insertions, 15 deletions

diff --git a/arch/arm/include/asm/arch-sunxi/clock_sun9i.h b/arch/arm/include/asm/arch-sunxi/clock_sun9i.h
index a61934fb36..fd166030dc 100644
--- a/arch/arm/include/asm/arch-sunxi/clock_sun9i.h
+++ b/arch/arm/include/asm/arch-sunxi/clock_sun9i.h
@@ -37,57 +37,61 @@ struct sunxi_ccm_reg {
 	u8 reserved3[0x04];	/* 0x7c */
 	u32 ats_cfg;		/* 0x80 ats clock configuration */
 	u32 trace_cfg;		/* 0x84 trace clock configuration */
-	u8 reserved4[0xf8];	/* 0x88 */
+	u8 reserved4[0x14];     /* 0x88 */
+	u32 pll_stable_status;  /* 0x9c */
+	u8 reserved5[0xe0];	/* 0xa0 */
 	u32 clk_output_a;	/* 0x180 clk_output_a */
 	u32 clk_output_b;	/* 0x184 clk_output_a */
-	u8 reserved5[0x278];	/* 0x188 */
+	u8 reserved6[0x278];	/* 0x188 */
 
 	u32 nand0_clk_cfg;	/* 0x400 nand0 clock configuration0 */
 	u32 nand0_clk_cfg1;	/* 0x404 nand1 clock configuration */
-	u8 reserved6[0x08];	/* 0x408 */
+	u8 reserved7[0x08];	/* 0x408 */
 	u32 sd0_clk_cfg;	/* 0x410 sd0 clock configuration */
 	u32 sd1_clk_cfg;	/* 0x414 sd1 clock configuration */
 	u32 sd2_clk_cfg;	/* 0x418 sd2 clock configuration */
 	u32 sd3_clk_cfg;	/* 0x41c sd3 clock configuration */
-	u8 reserved7[0x08];	/* 0x420 */
+	u8 reserved8[0x08];	/* 0x420 */
 	u32 ts_clk_cfg;		/* 0x428 transport stream clock cfg */
 	u32 ss_clk_cfg;		/* 0x42c security system clock cfg */
 	u32 spi0_clk_cfg;	/* 0x430 spi0 clock configuration */
 	u32 spi1_clk_cfg;	/* 0x434 spi1 clock configuration */
 	u32 spi2_clk_cfg;	/* 0x438 spi2 clock configuration */
 	u32 spi3_clk_cfg;	/* 0x43c spi3 clock configuration */
-	u8 reserved8[0x50];	/* 0x440 */
+	u8 reserved9[0x44];	/* 0x440 */
+	u32 dram_clk_cfg;       /* 0x484 DRAM (controller) clock config */
+	u8 reserved10[0x8];     /* 0x488 */
 	u32 de_clk_cfg;		/* 0x490 display engine clock configuration */
-	u8 reserved9[0x04];	/* 0x494 */
+	u8 reserved11[0x04];	/* 0x494 */
 	u32 mp_clk_cfg;		/* 0x498 mp clock configuration */
 	u32 lcd0_clk_cfg;	/* 0x49c LCD0 module clock */
 	u32 lcd1_clk_cfg;	/* 0x4a0 LCD1 module clock */
-	u8 reserved10[0x1c];	/* 0x4a4 */
+	u8 reserved12[0x1c];	/* 0x4a4 */
 	u32 csi_isp_clk_cfg;	/* 0x4c0 CSI ISP module clock */
 	u32 csi0_clk_cfg;	/* 0x4c4 CSI0 module clock */
 	u32 csi1_clk_cfg;	/* 0x4c8 CSI1 module clock */
 	u32 fd_clk_cfg;		/* 0x4cc FD module clock */
 	u32 ve_clk_cfg;		/* 0x4d0 VE module clock */
 	u32 avs_clk_cfg;	/* 0x4d4 AVS module clock */
-	u8 reserved11[0x18];	/* 0x4d8 */
+	u8 reserved13[0x18];	/* 0x4d8 */
 	u32 gpu_core_clk_cfg;	/* 0x4f0 GPU core clock config */
 	u32 gpu_mem_clk_cfg;	/* 0x4f4 GPU memory clock config */
 	u32 gpu_axi_clk_cfg;	/* 0x4f8 GPU AXI clock config */
-	u8 reserved12[0x10];	/* 0x4fc */
+	u8 reserved14[0x10];	/* 0x4fc */
 	u32 gp_adc_clk_cfg;	/* 0x50c General Purpose ADC clk config */
-	u8 reserved13[0x70];	/* 0x510 */
+	u8 reserved15[0x70];	/* 0x510 */
 
 	u32 ahb_gate0;		/* 0x580 AHB0 Gating Register */
 	u32 ahb_gate1;		/* 0x584 AHB1 Gating Register */
 	u32 ahb_gate2;		/* 0x588 AHB2 Gating Register */
-	u8 reserved14[0x04];	/* 0x58c */
+	u8 reserved16[0x04];	/* 0x58c */
 	u32 apb0_gate;		/* 0x590 APB0 Clock Gating Register */
 	u32 apb1_gate;		/* 0x594 APB1 Clock Gating Register */
-	u8 reserved15[0x08];	/* 0x598 */
+	u8 reserved17[0x08];	/* 0x598 */
 	u32 ahb_reset0_cfg;	/* 0x5a0 AHB0 Software Reset Register */
 	u32 ahb_reset1_cfg;	/* 0x5a4 AHB1 Software Reset Register */
 	u32 ahb_reset2_cfg;	/* 0x5a8 AHB2 Software Reset Register */
-	u8 reserved16[0x04];	/* 0x5ac */
+	u8 reserved18[0x04];	/* 0x5ac */
 	u32 apb0_reset_cfg;	/* 0x5b0 Bus Software Reset Register 3 */
 	u32 apb1_reset_cfg;	/* 0x5b4 Bus Software Reset Register 4 */
 };
@@ -112,6 +116,8 @@ struct sunxi_ccm_reg {
 #define CCM_MMC_CTRL_ENABLE		(1 << 31)
 
 /* ahb_gate0 fields */
+#define AHB_GATE_OFFSET_MCTL		14
+
 /* On sun9i all sdc-s share their ahb gate, so ignore (x) */
 #define AHB_GATE_OFFSET_NAND0		13
 #define AHB_GATE_OFFSET_MMC(x)		8
@@ -126,6 +132,8 @@ struct sunxi_ccm_reg {
 #define APB1_GATE_TWI_MASK		(0xf << APB1_GATE_TWI_SHIFT)
 
 /* ahb_reset0_cfg fields */
+#define AHB_RESET_OFFSET_MCTL		14
+
 /* On sun9i all sdc-s share their ahb reset, so ignore (x) */
 #define AHB_RESET_OFFSET_MMC(x)		8
 
diff --git a/arch/arm/include/asm/arch-sunxi/cpu_sun9i.h b/arch/arm/include/asm/arch-sunxi/cpu_sun9i.h
index 04889c51fa..acbc94f4c3 100644
--- a/arch/arm/include/asm/arch-sunxi/cpu_sun9i.h
+++ b/arch/arm/include/asm/arch-sunxi/cpu_sun9i.h
@@ -38,6 +38,12 @@
 #define SUNXI_ARMA9_GIC_BASE		(REGS_AHB0_BASE + 0x41000)
 #define SUNXI_ARMA9_CPUIF_BASE		(REGS_AHB0_BASE + 0x42000)
 
+#define SUNXI_DRAM_COM_BASE		(REGS_AHB0_BASE + 0x62000)
+#define SUNXI_DRAM_CTL0_BASE		(REGS_AHB0_BASE + 0x63000)
+#define SUNXI_DRAM_CTL1_BASE		(REGS_AHB0_BASE + 0x64000)
+#define SUNXI_DRAM_PHY0_BASE		(REGS_AHB0_BASE + 0x65000)
+#define SUNXI_DRAM_PHY1_BASE		(REGS_AHB0_BASE + 0x66000)
+
 /* AHB1 Module */
 #define SUNXI_DMA_BASE			(REGS_AHB1_BASE + 0x002000)
 #define SUNXI_USBOTG_BASE		(REGS_AHB1_BASE + 0x100000)
diff --git a/arch/arm/include/asm/arch-sunxi/dram.h b/arch/arm/include/asm/arch-sunxi/dram.h
index 675876ff6c..e0be744dba 100644
--- a/arch/arm/include/asm/arch-sunxi/dram.h
+++ b/arch/arm/include/asm/arch-sunxi/dram.h
@@ -26,6 +26,8 @@
 #include <asm/arch/dram_sun8i_a83t.h>
 #elif defined(CONFIG_MACH_SUN8I_H3)
 #include <asm/arch/dram_sun8i_h3.h>
+#elif defined(CONFIG_MACH_SUN9I)
+#include <asm/arch/dram_sun9i.h>
 #else
 #include <asm/arch/dram_sun4i.h>
 #endif
diff --git a/arch/arm/include/asm/arch-sunxi/dram_sun9i.h b/arch/arm/include/asm/arch-sunxi/dram_sun9i.h
new file mode 100644
index 0000000000..22be6bc397
--- /dev/null
+++ b/arch/arm/include/asm/arch-sunxi/dram_sun9i.h
@@ -0,0 +1,278 @@
+/*
+ * Sun8i platform dram controller register and constant defines
+ *
+ * (C) Copyright 2007-2015 Allwinner Technology Co.
+ *                         Jerry Wang <wangflord@allwinnertech.com>
+ * (C) Copyright 2016  Theobroma Systems Design und Consulting GmbH
+ *                     Philipp Tomsich <philipp.tomsich@theobroma-systems.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#ifndef _SUNXI_DRAM_SUN9I_H
+#define _SUNXI_DRAM_SUN9I_H
+
+struct sunxi_mctl_com_reg {
+	u32 cr;			/* 0x00 */
+	u32 ccr;		/* 0x04 controller configuration register */
+	u32 dbgcr;		/* 0x08 */
+	u32 dbgcr1;		/* 0x0c */
+	u32 rmcr;		/* 0x10 */
+	u8 res1[0x1c];		/* 0x14 */
+	u32 mmcr;		/* 0x30 */
+	u8 res2[0x3c];		/* 0x34 */
+	u32 mbagcr;		/* 0x70 */
+	u32 mbacr;		/* 0x74 */
+	u8 res3[0x10];		/* 0x78 */
+	u32 maer;		/* 0x88 */
+	u8 res4[0x74];		/* 0x8c */
+	u32 mdfscr;		/* 0x100 */
+	u32 mdfsmer;		/* 0x104 */
+	u32 mdfsmrmr;		/* 0x108 */
+	u32 mdfstr[4];		/* 0x10c */
+	u32 mdfsgcr;		/* 0x11c */
+	u8 res5[0x1c];		/* 0x120 */
+	u32 mdfsivr;		/* 0x13c */
+	u8 res6[0xc];		/* 0x140 */
+	u32 mdfstcr;		/* 0x14c */
+};
+
+
+struct sunxi_mctl_ctl_reg {
+	u32 mstr;		/* 0x00 master register */
+	u32 stat;		/* 0x04 operating mode status register */
+	u8 res1[0x8];		/* 0x08 */
+	u32 mrctrl[2];		/* 0x10 mode register read/write control reg */
+	u32 mstat;		/* 0x18 mode register read/write status reg */
+	u8 res2[0x4];		/* 0x1c */
+	u32 derateen;		/* 0x20 temperature derate enable register */
+	u32 derateint;		/* 0x24 temperature derate interval register */
+	u8 res3[0x8];		/* 0x28 */
+	u32 pwrctl;		/* 0x30 low power control register */
+	u32 pwrtmg;		/* 0x34 low power timing register */
+	u8 res4[0x18];		/* 0x38 */
+	u32 rfshctl0;		/* 0x50 refresh control register 0 */
+	u32 rfshctl1;		/* 0x54 refresh control register 1 */
+	u8 res5[0x8];		/* 0x58 */
+	u32 rfshctl3;		/* 0x60 refresh control register 3 */
+	u32 rfshtmg;		/* 0x64 refresh timing register */
+	u8 res6[0x68];		/* 0x68 */
+	u32 init[6];		/* 0xd0 SDRAM initialisation register */
+	u8 res7[0xc];		/* 0xe8 */
+	u32 rankctl;		/* 0xf4 rank control register */
+	u8 res8[0x8];		/* 0xf8 */
+	u32 dramtmg[9];		/* 0x100 DRAM timing register */
+	u8 res9[0x5c];		/* 0x124 */
+	u32 zqctrl[3];		/* 0x180 ZQ control register */
+	u32 zqstat;		/* 0x18c ZQ status register */
+	u32 dfitmg[2];		/* 0x190 DFI timing register */
+	u32 dfilpcfg;		/* 0x198 DFI low power configuration register */
+	u8 res10[0x4];		/* 0x19c */
+	u32 dfiupd[4];		/* 0x1a0 DFI update register */
+	u32 dfimisc;		/* 0x1b0 DFI miscellaneous control register */
+	u8 res11[0x1c];		/* 0x1b4 */
+	u32 trainctl[3];	/* 0x1d0 */
+	u32 trainstat;	        /* 0x1dc */
+	u8 res12[0x20];		/* 0x1e0 */
+	u32 addrmap[7];	        /* 0x200 address map register */
+	u8 res13[0x24];		/* 0x21c */
+	u32 odtcfg;		/* 0x240 ODT configuration register */
+	u32 odtmap;		/* 0x244 ODT/rank map register */
+	u8 res14[0x8];		/* 0x248 */
+	u32 sched;		/* 0x250 scheduler control register */
+	u8 res15[0x4];		/* 0x254 */
+	u32 perfhpr0;		/* 0x258 high priority read CAM register 0 */
+	u32 perfhpr1;		/* 0x25c high priority read CAM register 1 */
+	u32 perflpr0;		/* 0x260 low priority read CAM register 0 */
+	u32 perflpr1;		/* 0x264 low priority read CAM register 1 */
+	u32 perfwr0;		/* 0x268 write CAM register 0 */
+	u32 perfwr1;		/* 0x26c write CAM register 1 */
+};
+
+
+struct sunxi_mctl_phy_reg {
+	u8 res0[0x04];		/* 0x00 revision id ??? */
+	u32 pir;		/* 0x04 PHY initialisation register */
+	u32 pgcr[4];		/* 0x08 PHY general configuration register */
+	u32 pgsr[2];		/* 0x18 PHY general status register */
+	u32 pllcr;		/* 0x20 PLL control register */
+	u32 ptr[5];		/* 0x24 PHY timing register */
+	u32 acmdlr;		/* 0x38 AC master delay line register */
+	u32 aclcdlr;		/* 0x3c AC local calibrated delay line reg */
+	u32 acbdlr[10];		/* 0x40 AC bit delay line register */
+	u32 aciocr[6];		/* 0x68 AC IO configuration register */
+	u32 dxccr;		/* 0x80 DATX8 common configuration register */
+	u32 dsgcr;		/* 0x84 DRAM system general config register */
+	u32 dcr;		/* 0x88 DRAM configuration register */
+	u32 dtpr[4];		/* 0x8c DRAM timing parameters register */
+	u32 mr0;		/* 0x9c mode register 0 */
+	u32 mr1;		/* 0xa0 mode register 1 */
+	u32 mr2;		/* 0xa4 mode register 2 */
+	u32 mr3;		/* 0xa8 mode register 3 */
+	u32 odtcr;		/* 0xac ODT configuration register */
+	u32 dtcr;		/* 0xb0 data training configuration register */
+	u32 dtar[4];		/* 0xb4 data training address register */
+	u32 dtdr[2];		/* 0xc4 data training data register */
+	u32 dtedr[2];		/* 0xcc data training eye data register */
+	u32 rdimmgcr[2];	/* 0xd4 RDIMM general configuration register */
+	u32 rdimmcr[2];		/* 0xdc RDIMM control register */
+	u32 gpr[2];		/* 0xe4 general purpose register */
+	u32 catr[2];		/* 0xec CA training register */
+	u32 dqdsr;		/* 0xf4 DQS drift register */
+	u8 res1[0xc8];		/* 0xf8 */
+	u32 bistrr;		/* 0x1c0 BIST run register */
+	u32 bistwcr;		/* 0x1c4 BIST word count register */
+	u32 bistmskr[3];	/* 0x1c8 BIST mask register */
+	u32 bistlsr;		/* 0x1d4 BIST LFSR seed register */
+	u32 bistar[3];		/* 0x1d8 BIST address register */
+	u32 bistupdr;		/* 0x1e4 BIST user pattern data register */
+	u32 bistgsr;		/* 0x1e8 BIST general status register */
+	u32 bistwer;		/* 0x1dc BIST word error register */
+	u32 bistber[4];		/* 0x1f0 BIST bit error register */
+	u32 bistwcsr;		/* 0x200 BIST word count status register */
+	u32 bistfwr[3];		/* 0x204 BIST fail word register */
+	u8 res2[0x28];		/* 0x210 */
+	u32 iovcr[2];		/* 0x238 IO VREF control register */
+	struct ddrphy_zq {
+		u32 cr;              /* impedance control register */
+		u32 pr;              /* impedance control data register */
+		u32 dr;              /* impedance control data register */
+		u32 sr;              /* impedance control status register */
+	} zq[4];                /* 0x240, 0x250, 0x260, 0x270 */
+	struct ddrphy_dx {
+		u32 gcr[4];          /* DATX8 general configuration register */
+		u32 gsr[3];          /* DATX8 general status register */
+		u32 bdlr[7];         /* DATX8 bit delay line register */
+		u32 lcdlr[3];        /* DATX8 local calibrated delay line reg */
+		u32 mdlr;            /* DATX8 master delay line register */
+		u32 gtr;             /* DATX8 general timing register */
+		u8 res[0x34];
+	} dx[4];                /* 0x280, 0x300, 0x380, 0x400 */
+};
+
+/*
+ * DRAM common (sunxi_mctl_com_reg) register constants.
+ */
+#define MCTL_CR_RANK_MASK		(3 << 0)
+#define MCTL_CR_RANK(x)			(((x) - 1) << 0)
+#define MCTL_CR_BANK_MASK		(3 << 2)
+#define MCTL_CR_BANK(x)			((x) << 2)
+#define MCTL_CR_ROW_MASK		(0xf << 4)
+#define MCTL_CR_ROW(x)			(((x) - 1) << 4)
+#define MCTL_CR_PAGE_SIZE_MASK		(0xf << 8)
+#define MCTL_CR_PAGE_SIZE(x)		((fls(x) - 4) << 8)
+#define MCTL_CR_BUSW_MASK		(3 << 12)
+#define MCTL_CR_BUSW16			(1 << 12)
+#define MCTL_CR_BUSW32			(3 << 12)
+#define MCTL_CR_DRAMTYPE_MASK           (7 << 16)
+#define MCTL_CR_DRAMTYPE_DDR2		(2 << 16)
+#define MCTL_CR_DRAMTYPE_DDR3		(3 << 16)
+#define MCTL_CR_DRAMTYPE_LPDDR2		(6 << 16)
+
+#define MCTL_CR_CHANNEL_MASK		((1 << 22) | (1 << 20) | (1 << 19))
+#define MCTL_CR_CHANNEL_SINGLE          (1 << 22)
+#define MCTL_CR_CHANNEL_DUAL            ((1 << 22) | (1 << 20) | (1 << 19))
+
+#define MCTL_CCR_CH0_CLK_EN		(1 << 15)
+#define MCTL_CCR_CH1_CLK_EN		(1 << 31)
+
+/*
+ * post_cke_x1024 [bits 16..25]: Cycles to wait after driving CKE high
+ * to start the SDRAM initialization sequence (in 1024s of cycles).
+ */
+#define MCTL_INIT0_POST_CKE_x1024(n)    ((n & 0x0fff) << 16)
+/*
+ * pre_cke_x1024 [bits 0..11] Cycles to wait after reset before driving
+ * CKE high to start the SDRAM initialization (in 1024s of cycles)
+ */
+#define MCTL_INIT0_PRE_CKE_x1024(n)     ((n & 0x0fff) <<  0)
+#define MCTL_INIT1_DRAM_RSTN_x1024(n)   ((n & 0xff) << 16)
+#define MCTL_INIT1_FINAL_WAIT_x32(n)    ((n & 0x3f) <<  8)
+#define MCTL_INIT1_PRE_OCD_x32(n)       ((n & 0x0f) <<  0)
+#define MCTL_INIT2_IDLE_AFTER_RESET_x32(n)  ((n & 0xff) << 8)
+#define MCTL_INIT2_MIN_STABLE_CLOCK_x1(n)   ((n & 0x0f) << 0)
+#define MCTL_INIT3_MR(n)                ((n & 0xffff) << 16)
+#define MCTL_INIT3_EMR(n)               ((n & 0xffff) <<  0)
+#define MCTL_INIT4_EMR2(n)              ((n & 0xffff) << 16)
+#define MCTL_INIT4_EMR3(n)              ((n & 0xffff) <<  0)
+#define MCTL_INIT5_DEV_ZQINIT_x32(n)        ((n & 0x00ff) << 16)
+#define MCTL_INIT5_MAX_AUTO_INIT_x1024(n)   ((n & 0x03ff) <<  0);
+
+#define MCTL_DFIMISC_DFI_INIT_COMPLETE_EN  (1 << 0)
+#define MCTL_DFIUPD0_DIS_AUTO_CTRLUPD      (1 << 31)
+
+#define MCTL_MSTR_DEVICETYPE_DDR3          1
+#define MCTL_MSTR_DEVICETYPE_LPDDR2        4
+#define MCTL_MSTR_DEVICETYPE_LPDDR3        8
+#define MCTL_MSTR_DEVICETYPE(type) \
+	((type == DRAM_TYPE_DDR3) ? MCTL_MSTR_DEVICETYPE_DDR3 : \
+		((type == DRAM_TYPE_LPDDR2) ? MCTL_MSTR_DEVICETYPE_LPDDR2 : \
+					      MCTL_MSTR_DEVICETYPE_LPDDR3))
+#define MCTL_MSTR_BURSTLENGTH4             (2 << 16)
+#define MCTL_MSTR_BURSTLENGTH8             (4 << 16)
+#define MCTL_MSTR_BURSTLENGTH16            (8 << 16)
+#define MCTL_MSTR_BURSTLENGTH(type) \
+	((type == DRAM_TYPE_DDR3) ? MCTL_MSTR_BURSTLENGTH8 : \
+		((type == DRAM_TYPE_LPDDR2) ? MCTL_MSTR_BURSTLENGTH4 : \
+					      MCTL_MSTR_BURSTLENGTH8))
+#define MCTL_MSTR_ACTIVERANKS(x)           (((x == 2) ? 3 : 1) << 24)
+#define MCTL_MSTR_BUSWIDTH8                (2 << 12)
+#define MCTL_MSTR_BUSWIDTH16               (1 << 12)
+#define MCTL_MSTR_BUSWIDTH32               (0 << 12)
+#define MCTL_MSTR_2TMODE                   (1 << 10)
+
+#define MCTL_RFSHCTL3_DIS_AUTO_REFRESH     (1 << 0)
+
+#define MCTL_ZQCTRL0_TZQCS(x)              (x << 0)
+#define MCTL_ZQCTRL0_TZQCL(x)              (x << 16)
+#define MCTL_ZQCTRL0_ZQCL_DIS              (1 << 30)
+#define MCTL_ZQCTRL0_ZQCS_DIS              (1 << 31)
+#define MCTL_ZQCTRL1_TZQRESET(x)           (x << 20)
+#define MCTL_ZQCTRL1_TZQSI_x1024(x)        (x << 0)
+#define MCTL_ZQCTRL2_TZRESET_TRIGGER       (1 << 0)
+
+#define MCTL_PHY_DCR_BYTEMASK              (1 << 10)
+#define MCTL_PHY_DCR_2TMODE                (1 << 28)
+#define MCTL_PHY_DCR_DDR8BNK               (1 << 3)
+#define MCTL_PHY_DRAMMODE_DDR3             3
+#define MCTL_PHY_DRAMMODE_LPDDR2           0
+#define MCTL_PHY_DRAMMODE_LPDDR3           1
+
+#define MCTL_DTCR_DEFAULT                  0x00003007
+#define MCTL_DTCR_RANKEN(n)                (((n == 2) ? 3 : 1) << 24)
+
+#define MCTL_PGCR1_ZCKSEL_MASK             (3 << 23)
+#define MCTL_PGCR1_IODDRM_MASK             (3 << 7)
+#define MCTL_PGCR1_IODDRM_DDR3             (1 << 7)
+#define MCTL_PGCR1_IODDRM_DDR3L            (2 << 7)
+#define MCTL_PGCR1_INHVT_EN                (1 << 26)
+
+#define MCTL_PLLGCR_PLL_BYPASS             (1 << 31)
+#define MCTL_PLLGCR_PLL_POWERDOWN          (1 << 29)
+
+#define MCTL_PIR_PLL_BYPASS                (1 << 17)
+#define MCTL_PIR_MASK                      (~(1 << 17))
+#define MCTL_PIR_INIT                      (1 << 0)
+
+#define MCTL_PGSR0_ERRORS                  (0x1ff << 20)
+
+/* Constants for assembling MR0 */
+#define DDR3_MR0_PPD_FAST_EXIT             (1 << 12)
+#define DDR3_MR0_WR(n) \
+	((n <= 8) ? ((n - 4) << 9) : (((n >> 1) & 0x7) << 9))
+#define DDR3_MR0_CL(n) \
+	((((n - 4) & 0x7) << 4) | (((n - 4) & 0x8) >> 2))
+#define DDR3_MR0_BL8                       (0 << 0)
+
+#define DDR3_MR1_RTT120OHM                 ((0 << 9) | (1 << 6) | (0 << 2))
+
+#define DDR3_MR2_TWL(n) \
+	(((n - 5) & 0x7) << 3)
+
+#define MCTL_NS2CYCLES_CEIL(ns)	((ns * (CONFIG_DRAM_CLK / 2) + 999) / 1000)
+
+#define DRAM_TYPE_DDR3		3
+#define DRAM_TYPE_LPDDR2	6
+#define DRAM_TYPE_LPDDR3	7
+
+#endif
diff --git a/arch/arm/mach-sunxi/Makefile b/arch/arm/mach-sunxi/Makefile
index 25367cf380..9d07d6b84c 100644
--- a/arch/arm/mach-sunxi/Makefile
+++ b/arch/arm/mach-sunxi/Makefile
@@ -49,4 +49,5 @@ obj-$(CONFIG_MACH_SUN8I_A23)	+= dram_sun8i_a23.o
 obj-$(CONFIG_MACH_SUN8I_A33)	+= dram_sun8i_a33.o
 obj-$(CONFIG_MACH_SUN8I_A83T)	+= dram_sun8i_a83t.o
 obj-$(CONFIG_MACH_SUN8I_H3)	+= dram_sun8i_h3.o
+obj-$(CONFIG_MACH_SUN9I)	+= dram_sun9i.o
 endif
diff --git a/arch/arm/mach-sunxi/dram_sun9i.c b/arch/arm/mach-sunxi/dram_sun9i.c
new file mode 100644
index 0000000000..8c681f3541
--- /dev/null
+++ b/arch/arm/mach-sunxi/dram_sun9i.c
@@ -0,0 +1,961 @@
+/*
+ * sun9i dram controller initialisation
+ *
+ * (C) Copyright 2007-2015
+ * Allwinner Technology Co., Ltd. <www.allwinnertech.com>
+ * Jerry Wang <wangflord@allwinnertech.com>
+ *
+ * (C) Copyright 2016 Theobroma Systems Design und Consulting GmbH
+ *                    Philipp Tomsich <philipp.tomsich@theobroma-systems.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <dm.h>
+#include <errno.h>
+#include <ram.h>
+#include <asm/io.h>
+#include <asm/arch/clock.h>
+#include <asm/arch/dram.h>
+#include <asm/arch/sys_proto.h>
+
+DECLARE_GLOBAL_DATA_PTR;
+
+#define DRAM_CLK (CONFIG_DRAM_CLK * 1000000)
+
+/*
+ * The following amounts to an extensive rewrite of the code received from
+ * Allwinner as part of the open-source bootloader release (refer to
+ * https://github.com/allwinner-zh/bootloader.git) and augments the upstream
+ * sources (which act as the primary reference point for the inner workings
+ * of the 'underdocumented' DRAM controller in the A80) using the following
+ * documentation for other memory controllers based on the (Synopsys)
+ * Designware IP (DDR memory protocol controller and DDR PHY)
+ *   * TI Keystone II Architecture: DDR3 Memory Controller, User's Guide
+ *     Document 'SPRUHN7C', Oct 2013 (revised March 2015)
+ *   * Xilinx Zynq UltraScale+ MPSoC Register Reference
+ *     document ug1087 (v1.0)
+ * Note that the Zynq-documentation provides a very close match for the DDR
+ * memory protocol controller (and provides a very good guide to the rounding
+ * rules for various timings), whereas the TI Keystone II document should be
+ * referred to for DDR PHY specifics only.
+ *
+ * The DRAM controller in the A80 runs at half the frequency of the DDR PHY
+ * (i.e. the rules for MEMC_FREQ_RATIO=2 from the Zynq-documentation apply).
+ *
+ * Known limitations
+ * =================
+ * In the current state, the following features are not fully supported and
+ * a number of simplifying assumptions have been made:
+ *   1) Only DDR3 support is implemented, as our test platform (the A80-Q7
+ *      module) is designed to accomodate DDR3/DDR3L.
+ *   2) Only 2T-mode has been implemented and tested.
+ *   3) The controller supports two different clocking strategies (PLL6 can
+ *      either be 2*CK or CK/2)... we only support the 2*CK clock at this
+ *      time and haven't verified whether the alternative clocking strategy
+ *      works.  If you are interested in porting this over/testing this,
+ *      please refer to cases where bit 0 of 'dram_tpr8' is tested in the
+ *      original code from Allwinner.
+ *   4) Support for 2 ranks per controller is not implemented (as we don't
+ *      the hardware to test it).
+ *
+ * Future directions
+ * =================
+ * The driver should be driven from a device-tree based configuration that
+ * can dynamically provide the necessary timing parameters (i.e. target
+ * frequency and speed-bin information)---the data structures used in the
+ * calculation of the timing parameters are already designed to capture
+ * similar information as the device tree would provide.
+ *
+ * To enable a device-tree based configuration of the sun9i platform, we
+ * will need to enable CONFIG_TPL and bootstrap in 3 stages: initially
+ * into SRAM A1 (40KB) and next into SRAM A2 (160KB)---which would be the
+ * stage to initialise the platform via the device-tree---before having
+ * the full U-Boot run from DDR.
+ */
+
+/*
+ * A number of DDR3 timings are given as "the greater of a fixed number of
+ * clock cycles (CK) or nanoseconds.  We express these using a structure
+ * that holds a cycle count and a duration in picoseconds (so we can model
+ * sub-ns timings, such as 7.5ns without losing precision or resorting to
+ * rounding up early.
+ */
+struct dram_sun9i_timing {
+	u32 ck;
+	u32 ps;
+};
+
+/* */
+struct dram_sun9i_cl_cwl_timing {
+	u32 CL;
+	u32 CWL;
+	u32 tCKmin;  /* in ps */
+	u32 tCKmax;  /* in ps */
+};
+
+struct dram_sun9i_para {
+	u32 dram_type;
+
+	u8 bus_width;
+	u8 chan;
+	u8 rank;
+	u8 rows;
+	u16 page_size;
+
+	/* Timing information for each speed-bin */
+	struct dram_sun9i_cl_cwl_timing *cl_cwl_table;
+	u32 cl_cwl_numentries;
+
+	/*
+	 * For the timings, we try to keep the order and grouping used in
+	 * JEDEC Standard No. 79-3F
+	 */
+
+	/* timings */
+	u32 tREFI; /* in ns */
+	u32 tRFC;  /* in ns */
+
+	u32 tRAS;  /* in ps */
+
+	/* command and address timing */
+	u32 tDLLK; /* in nCK */
+	struct dram_sun9i_timing tRTP;
+	struct dram_sun9i_timing tWTR;
+	u32 tWR;   /* in nCK */
+	u32 tMRD;  /* in nCK */
+	struct dram_sun9i_timing tMOD;
+	u32 tRCD;  /* in ps */
+	u32 tRP;   /* in ps */
+	u32 tRC;   /* in ps */
+	u32 tCCD;  /* in nCK */
+	struct dram_sun9i_timing tRRD;
+	u32 tFAW;  /* in ps */
+
+	/* calibration timing */
+	/* struct dram_sun9i_timing tZQinit; */
+	struct dram_sun9i_timing tZQoper;
+	struct dram_sun9i_timing tZQCS;
+
+	/* reset timing */
+	/* struct dram_sun9i_timing tXPR; */
+
+	/* self-refresh timings */
+	struct dram_sun9i_timing tXS;
+	u32 tXSDLL; /* in nCK */
+	/* struct dram_sun9i_timing tCKESR; */
+	struct dram_sun9i_timing tCKSRE;
+	struct dram_sun9i_timing tCKSRX;
+
+	/* power-down timings */
+	struct dram_sun9i_timing tXP;
+	struct dram_sun9i_timing tXPDLL;
+	struct dram_sun9i_timing tCKE;
+
+	/* write leveling timings */
+	u32 tWLMRD;    /* min, in nCK */
+	/* u32 tWLDQSEN;  min, in nCK */
+	u32 tWLO;      /* max, in ns */
+	/* u32 tWLOE;     max, in ns */
+
+	/* u32 tCKDPX;    in nCK */
+	/* u32 tCKCSX;    in nCK */
+};
+
+static void mctl_sys_init(void);
+
+#define SCHED_RDWR_IDLE_GAP(n)            ((n & 0xff) << 24)
+#define SCHED_GO2CRITICAL_HYSTERESIS(n)   ((n & 0xff) << 16)
+#define SCHED_LPR_NUM_ENTRIES(n)          ((n & 0xff) <<  8)
+#define SCHED_PAGECLOSE                   (1 << 2)
+#define SCHED_PREFER_WRITE                (1 << 1)
+#define SCHED_FORCE_LOW_PRI_N             (1 << 0)
+
+#define SCHED_CONFIG		(SCHED_RDWR_IDLE_GAP(0xf) | \
+				 SCHED_GO2CRITICAL_HYSTERESIS(0x80) | \
+				 SCHED_LPR_NUM_ENTRIES(0x20) | \
+				 SCHED_FORCE_LOW_PRI_N)
+#define PERFHPR0_CONFIG                   0x0000001f
+#define PERFHPR1_CONFIG                   0x1f00001f
+#define PERFLPR0_CONFIG                   0x000000ff
+#define PERFLPR1_CONFIG                   0x0f0000ff
+#define PERFWR0_CONFIG                    0x000000ff
+#define PERFWR1_CONFIG                    0x0f0001ff
+
+static void mctl_ctl_sched_init(unsigned long  base)
+{
+	struct sunxi_mctl_ctl_reg *mctl_ctl =
+		(struct sunxi_mctl_ctl_reg *)base;
+
+	/* Needs to be done before the global clk enable... */
+	writel(SCHED_CONFIG, &mctl_ctl->sched);
+	writel(PERFHPR0_CONFIG, &mctl_ctl->perfhpr0);
+	writel(PERFHPR1_CONFIG, &mctl_ctl->perfhpr1);
+	writel(PERFLPR0_CONFIG, &mctl_ctl->perflpr0);
+	writel(PERFLPR1_CONFIG, &mctl_ctl->perflpr1);
+	writel(PERFWR0_CONFIG, &mctl_ctl->perfwr0);
+	writel(PERFWR1_CONFIG, &mctl_ctl->perfwr1);
+}
+
+static void mctl_sys_init(void)
+{
+	struct sunxi_ccm_reg * const ccm =
+		(struct sunxi_ccm_reg *)SUNXI_CCM_BASE;
+	struct sunxi_mctl_com_reg * const mctl_com =
+		(struct sunxi_mctl_com_reg *)SUNXI_DRAM_COM_BASE;
+
+	debug("Setting PLL6 to %d\n", DRAM_CLK * 2);
+	clock_set_pll6(DRAM_CLK * 2);
+
+	/* Original dram init code which may come in handy later
+	********************************************************
+	clock_set_pll6(use_2channelPLL ? (DRAM_CLK * 2) :
+					 (DRAM_CLK / 2), false);
+
+	if ((para->dram_clk <= 400)|((para->dram_tpr8 & 0x1)==0)) {
+		 * PLL6 should be 2*CK *
+		 * ccm_setup_pll6_ddr_clk(PLL6_DDR_CLK); *
+		ccm_setup_pll6_ddr_clk((1000000 * (para->dram_clk) * 2), 0);
+	} else {
+		 * PLL6 should be CK/2 *
+		ccm_setup_pll6_ddr_clk((1000000 * (para->dram_clk) / 2), 1);
+	}
+
+	if (para->dram_tpr13 & (0xf<<18)) {
+		 *
+		 * bit21:bit18=0001:pll swing 0.4
+		 * bit21:bit18=0010:pll swing 0.3
+		 * bit21:bit18=0100:pll swing 0.2
+		 * bit21:bit18=1000:pll swing 0.1
+		 *
+		dram_dbg("DRAM fre extend open !\n");
+		reg_val=mctl_read_w(CCM_PLL6_DDR_REG);
+		reg_val&=(0x1<<16);
+		reg_val=reg_val>>16;
+
+		if(para->dram_tpr13 & (0x1<<18))
+		{
+			mctl_write_w(CCM_PLL_BASE + 0x114,
+				(0x3333U|(0x3<<17)|(reg_val<<19)|(0x120U<<20)|
+				(0x2U<<29)|(0x1U<<31)));
+		}
+		else if(para->dram_tpr13 & (0x1<<19))
+		{
+			mctl_write_w(CCM_PLL_BASE + 0x114,
+				(0x6666U|(0x3U<<17)|(reg_val<<19)|(0xD8U<<20)|
+				(0x2U<<29)|(0x1U<<31)));
+		}
+		else if(para->dram_tpr13 & (0x1<<20))
+		{
+			mctl_write_w(CCM_PLL_BASE + 0x114,
+				(0x9999U|(0x3U<<17)|(reg_val<<19)|(0x90U<<20)|
+				(0x2U<<29)|(0x1U<<31)));
+		}
+		else if(para->dram_tpr13 & (0x1<<21))
+		{
+			mctl_write_w(CCM_PLL_BASE + 0x114,
+				(0xccccU|(0x3U<<17)|(reg_val<<19)|(0x48U<<20)|
+				(0x2U<<29)|(0x1U<<31)));
+		}
+
+		//frequency extend open
+		reg_val = mctl_read_w(CCM_PLL6_DDR_REG);
+		reg_val |= ((0x1<<24)|(0x1<<30));
+		mctl_write_w(CCM_PLL6_DDR_REG, reg_val);
+
+
+		while(mctl_read_w(CCM_PLL6_DDR_REG) & (0x1<<30));
+	}
+
+	aw_delay(0x20000);	//make some delay
+	********************************************************
+	*/
+
+	/* assert mctl reset */
+	clrbits_le32(&ccm->ahb_reset0_cfg, 1 << AHB_RESET_OFFSET_MCTL);
+	/* stop mctl clock */
+	clrbits_le32(&ccm->ahb_gate0, 1 << AHB_GATE_OFFSET_MCTL);
+
+	sdelay(2000);
+
+	/* deassert mctl reset */
+	setbits_le32(&ccm->ahb_reset0_cfg, 1 << AHB_RESET_OFFSET_MCTL);
+	/* enable mctl clock */
+	setbits_le32(&ccm->ahb_gate0, 1 << AHB_GATE_OFFSET_MCTL);
+
+	/* set up the transactions scheduling before enabling the global clk */
+	mctl_ctl_sched_init(SUNXI_DRAM_CTL0_BASE);
+	mctl_ctl_sched_init(SUNXI_DRAM_CTL1_BASE);
+	sdelay(1000);
+
+	debug("2\n");
+
+	/* (3 << 12): PLL_DDR */
+	writel((3 << 12) | (1 << 16), &ccm->dram_clk_cfg);
+	do {
+		debug("Waiting for DRAM_CLK_CFG\n");
+		sdelay(10000);
+	} while (readl(&ccm->dram_clk_cfg) & (1 << 16));
+	setbits_le32(&ccm->dram_clk_cfg, (1 << 31));
+
+	/* TODO: we only support the common case ... i.e. 2*CK */
+	setbits_le32(&mctl_com->ccr, (1 << 14) | (1 << 30));
+	writel(2, &mctl_com->rmcr); /* controller clock is PLL6/4 */
+
+	sdelay(2000);
+
+	/* Original dram init code which may come in handy later
+	********************************************************
+	if ((para->dram_clk <= 400) | ((para->dram_tpr8 & 0x1) == 0)) {
+		 * PLL6 should be 2*CK *
+		 * gating 2 channel pll *
+		reg_val = mctl_read_w(MC_CCR);
+		reg_val |= ((0x1 << 14) | (0x1U << 30));
+		mctl_write_w(MC_CCR, reg_val);
+		mctl_write_w(MC_RMCR, 0x2); * controller clock use pll6/4 *
+	} else {
+		 * enable 2 channel pll *
+		reg_val = mctl_read_w(MC_CCR);
+		reg_val &= ~((0x1 << 14) | (0x1U << 30));
+		mctl_write_w(MC_CCR, reg_val);
+		mctl_write_w(MC_RMCR, 0x0); * controller clock use pll6 *
+	}
+
+	reg_val = mctl_read_w(MC_CCR);
+	reg_val &= ~((0x1<<15)|(0x1U<<31));
+	mctl_write_w(MC_CCR, reg_val);
+	aw_delay(20);
+	//aw_delay(0x10);
+	********************************************************
+	*/
+
+	clrbits_le32(&mctl_com->ccr, MCTL_CCR_CH0_CLK_EN | MCTL_CCR_CH1_CLK_EN);
+	sdelay(1000);
+
+	setbits_le32(&mctl_com->ccr, MCTL_CCR_CH0_CLK_EN);
+	/* TODO if (para->chan == 2) */
+	setbits_le32(&mctl_com->ccr, MCTL_CCR_CH1_CLK_EN);
+}
+
+static void mctl_com_init(struct dram_sun9i_para *para)
+{
+	struct sunxi_mctl_com_reg * const mctl_com =
+		(struct sunxi_mctl_com_reg *)SUNXI_DRAM_COM_BASE;
+
+	/* TODO: hard-wired for DDR3 now */
+	writel(((para->chan == 2) ? MCTL_CR_CHANNEL_DUAL :
+				    MCTL_CR_CHANNEL_SINGLE)
+	       | MCTL_CR_DRAMTYPE_DDR3 | MCTL_CR_BANK(1)
+	       | MCTL_CR_ROW(para->rows)
+	       | ((para->bus_width == 32) ? MCTL_CR_BUSW32 : MCTL_CR_BUSW16)
+	       | MCTL_CR_PAGE_SIZE(para->page_size) | MCTL_CR_RANK(para->rank),
+	       &mctl_com->cr);
+
+	debug("CR: %d\n", readl(&mctl_com->cr));
+}
+
+static u32 mctl_channel_init(u32 ch_index, struct dram_sun9i_para *para)
+{
+	struct sunxi_mctl_ctl_reg *mctl_ctl;
+	struct sunxi_mctl_phy_reg *mctl_phy;
+
+	u32 CL = 0;
+	u32 CWL = 0;
+	u16 mr[4] = { 0, };
+
+#define PS2CYCLES_FLOOR(n)    ((n * CONFIG_DRAM_CLK) / 1000000)
+#define PS2CYCLES_ROUNDUP(n)  ((n * CONFIG_DRAM_CLK + 999999) / 1000000)
+#define NS2CYCLES_FLOOR(n)    ((n * CONFIG_DRAM_CLK) / 1000)
+#define NS2CYCLES_ROUNDUP(n)  ((n * CONFIG_DRAM_CLK + 999) / 1000)
+#define MAX(a, b)             ((a) > (b) ? (a) : (b))
+
+	/*
+	 * Convert the values to cycle counts (nCK) from what is provided
+	 * by the definition of each speed bin.
+	 */
+	/* const u32 tREFI = NS2CYCLES_FLOOR(para->tREFI); */
+	const u32 tREFI = NS2CYCLES_FLOOR(para->tREFI);
+	const u32 tRFC  = NS2CYCLES_ROUNDUP(para->tRFC);
+	const u32 tRCD  = PS2CYCLES_ROUNDUP(para->tRCD);
+	const u32 tRP   = PS2CYCLES_ROUNDUP(para->tRP);
+	const u32 tRC   = PS2CYCLES_ROUNDUP(para->tRC);
+	const u32 tRAS  = PS2CYCLES_ROUNDUP(para->tRAS);
+
+	/* command and address timing */
+	const u32 tDLLK = para->tDLLK;
+	const u32 tRTP  = MAX(para->tRTP.ck, PS2CYCLES_ROUNDUP(para->tRTP.ps));
+	const u32 tWTR  = MAX(para->tWTR.ck, PS2CYCLES_ROUNDUP(para->tWTR.ps));
+	const u32 tWR   = NS2CYCLES_FLOOR(para->tWR);
+	const u32 tMRD  = para->tMRD;
+	const u32 tMOD  = MAX(para->tMOD.ck, PS2CYCLES_ROUNDUP(para->tMOD.ps));
+	const u32 tCCD  = para->tCCD;
+	const u32 tRRD  = MAX(para->tRRD.ck, PS2CYCLES_ROUNDUP(para->tRRD.ps));
+	const u32 tFAW  = PS2CYCLES_ROUNDUP(para->tFAW);
+
+	/* calibration timings */
+	/* const u32 tZQinit = MAX(para->tZQinit.ck,
+				PS2CYCLES_ROUNDUP(para->tZQinit.ps)); */
+	const u32 tZQoper = MAX(para->tZQoper.ck,
+				PS2CYCLES_ROUNDUP(para->tZQoper.ps));
+	const u32 tZQCS   = MAX(para->tZQCS.ck,
+				PS2CYCLES_ROUNDUP(para->tZQCS.ps));
+
+	/* reset timing */
+	/* const u32 tXPR  = MAX(para->tXPR.ck,
+				PS2CYCLES_ROUNDUP(para->tXPR.ps)); */
+
+	/* power-down timings */
+	const u32 tXP    = MAX(para->tXP.ck, PS2CYCLES_ROUNDUP(para->tXP.ps));
+	const u32 tXPDLL = MAX(para->tXPDLL.ck,
+			       PS2CYCLES_ROUNDUP(para->tXPDLL.ps));
+	const u32 tCKE   = MAX(para->tCKE.ck, PS2CYCLES_ROUNDUP(para->tCKE.ps));
+
+	/*
+	 * self-refresh timings (keep below power-down timings, as tCKESR
+	 * needs to be calculated based on the nCK value of tCKE)
+	 */
+	const u32 tXS    = MAX(para->tXS.ck, PS2CYCLES_ROUNDUP(para->tXS.ps));
+	const u32 tXSDLL = para->tXSDLL;
+	const u32 tCKSRE = MAX(para->tCKSRE.ck,
+			       PS2CYCLES_ROUNDUP(para->tCKSRE.ps));
+	const u32 tCKESR = tCKE + 1;
+	const u32 tCKSRX = MAX(para->tCKSRX.ck,
+			       PS2CYCLES_ROUNDUP(para->tCKSRX.ps));
+
+	/* write leveling timings */
+	const u32 tWLMRD = para->tWLMRD;
+	/* const u32 tWLDQSEN = para->tWLDQSEN; */
+	const u32 tWLO = PS2CYCLES_FLOOR(para->tWLO);
+	/* const u32 tWLOE = PS2CYCLES_FLOOR(para->tWLOE); */
+
+	const u32 tRASmax = tREFI * 9;
+	int i;
+
+	for (i = 0; i < para->cl_cwl_numentries; ++i) {
+		const u32 tCK = 1000000 / CONFIG_DRAM_CLK;
+
+		if ((para->cl_cwl_table[i].tCKmin <= tCK) &&
+		    (tCK < para->cl_cwl_table[i].tCKmax)) {
+			CL = para->cl_cwl_table[i].CL;
+			CWL = para->cl_cwl_table[i].CWL;
+
+			debug("found CL/CWL: CL = %d, CWL = %d\n", CL, CWL);
+			break;
+		}
+	}
+
+	if ((CL == 0) && (CWL == 0)) {
+		printf("failed to find valid CL/CWL for operating point %d MHz\n",
+		       CONFIG_DRAM_CLK);
+		return 0;
+	}
+
+	if (ch_index == 0) {
+		mctl_ctl = (struct sunxi_mctl_ctl_reg *)SUNXI_DRAM_CTL0_BASE;
+		mctl_phy = (struct sunxi_mctl_phy_reg *)SUNXI_DRAM_PHY0_BASE;
+	} else {
+		mctl_ctl = (struct sunxi_mctl_ctl_reg *)SUNXI_DRAM_CTL1_BASE;
+		mctl_phy = (struct sunxi_mctl_phy_reg *)SUNXI_DRAM_PHY1_BASE;
+	}
+
+	if (para->dram_type == DRAM_TYPE_DDR3) {
+		mr[0] = DDR3_MR0_PPD_FAST_EXIT | DDR3_MR0_WR(tWR) |
+			DDR3_MR0_CL(CL);
+		mr[1] = DDR3_MR1_RTT120OHM;
+		mr[2] = DDR3_MR2_TWL(CWL);
+		mr[3] = 0;
+
+		/*
+		 * DRAM3 initialisation requires holding CKE LOW for
+		 * at least 500us prior to starting the initialisation
+		 * sequence and at least 10ns after driving CKE HIGH
+		 * before the initialisation sequence may be started).
+		 *
+		 * Refer to Micron document "TN-41-07: DDR3 Power-Up,
+		 * Initialization, and Reset DDR3 Initialization
+		 * Routine" for details).
+		 */
+		writel(MCTL_INIT0_POST_CKE_x1024(1) |
+		       MCTL_INIT0_PRE_CKE_x1024(
+			    (500 * CONFIG_DRAM_CLK + 1023) / 1024), /* 500us */
+		       &mctl_ctl->init[0]);
+		writel(MCTL_INIT1_DRAM_RSTN_x1024(1),
+		       &mctl_ctl->init[1]);
+		/* INIT2 is not used for DDR3 */
+		writel(MCTL_INIT3_MR(mr[0]) | MCTL_INIT3_EMR(mr[1]),
+		       &mctl_ctl->init[3]);
+		writel(MCTL_INIT4_EMR2(mr[2]) | MCTL_INIT4_EMR3(mr[3]),
+		       &mctl_ctl->init[4]);
+		writel(MCTL_INIT5_DEV_ZQINIT_x32(512 / 32), /* 512 cycles */
+		       &mctl_ctl->init[5]);
+	} else {
+		/* !!! UNTESTED !!! */
+		/*
+		 * LPDDR2 and/or LPDDR3 require a 200us minimum delay
+		 * after driving CKE HIGH in the initialisation sequence.
+		 */
+		writel(MCTL_INIT0_POST_CKE_x1024(
+				(200 * CONFIG_DRAM_CLK + 1023) / 1024),
+		       &mctl_ctl->init[0]);
+		writel(MCTL_INIT1_DRAM_RSTN_x1024(1),
+		       &mctl_ctl->init[1]);
+		writel(MCTL_INIT2_IDLE_AFTER_RESET_x32(
+				(CONFIG_DRAM_CLK + 31) / 32) /* 1us */
+		       | MCTL_INIT2_MIN_STABLE_CLOCK_x1(5),  /* 5 cycles */
+		       &mctl_ctl->init[2]);
+		writel(MCTL_INIT3_MR(mr[1]) | MCTL_INIT3_EMR(mr[2]),
+		       &mctl_ctl->init[3]);
+		writel(MCTL_INIT4_EMR2(mr[3]),
+		       &mctl_ctl->init[4]);
+		writel(MCTL_INIT5_DEV_ZQINIT_x32(
+				(CONFIG_DRAM_CLK + 31) / 32) /* 1us */
+		       | MCTL_INIT5_MAX_AUTO_INIT_x1024(
+				(10 * CONFIG_DRAM_CLK + 1023) / 1024),
+		       &mctl_ctl->init[5]);
+	}
+
+	/* (DDR3) We always use a burst-length of 8. */
+#define MCTL_BL               8
+	/* wr2pre: WL + BL/2 + tWR */
+#define WR2PRE           (MCTL_BL/2 + CWL + tWTR)
+	/* wr2rd = CWL + BL/2 + tWTR */
+#define WR2RD            (MCTL_BL/2 + CWL + tWTR)
+	/*
+	 * rd2wr = RL + BL/2 + 2 - WL (for DDR3)
+	 * rd2wr = RL + BL/2 + RU(tDQSCKmax/tCK) + 1 - WL (for LPDDR2/LPDDR3)
+	 */
+#define RD2WR            (CL + MCTL_BL/2 + 2 - CWL)
+#define MCTL_PHY_TRTW        0
+#define MCTL_PHY_TRTODT      0
+
+#define MCTL_DIV2(n)         ((n + 1)/2)
+#define MCTL_DIV32(n)        (n/32)
+#define MCTL_DIV1024(n)      (n/1024)
+
+	writel((MCTL_DIV2(WR2PRE) << 24) | (MCTL_DIV2(tFAW) << 16) |
+	       (MCTL_DIV1024(tRASmax) << 8) | (MCTL_DIV2(tRAS) << 0),
+	       &mctl_ctl->dramtmg[0]);
+	writel((MCTL_DIV2(tXP) << 16) | (MCTL_DIV2(tRTP) << 8) |
+	       (MCTL_DIV2(tRC) << 0),
+	       &mctl_ctl->dramtmg[1]);
+	writel((MCTL_DIV2(CWL) << 24) | (MCTL_DIV2(CL) << 16) |
+	       (MCTL_DIV2(RD2WR) << 8) | (MCTL_DIV2(WR2RD) << 0),
+	       &mctl_ctl->dramtmg[2]);
+	/*
+	 * Note: tMRW is located at bit 16 (and up) in DRAMTMG3...
+	 * this is only relevant for LPDDR2/LPDDR3
+	 */
+	writel((MCTL_DIV2(tMRD) << 12) | (MCTL_DIV2(tMOD) << 0),
+	       &mctl_ctl->dramtmg[3]);
+	writel((MCTL_DIV2(tRCD) << 24) | (MCTL_DIV2(tCCD) << 16) |
+	       (MCTL_DIV2(tRRD) << 8) | (MCTL_DIV2(tRP) << 0),
+	       &mctl_ctl->dramtmg[4]);
+	writel((MCTL_DIV2(tCKSRX) << 24) | (MCTL_DIV2(tCKSRE) << 16) |
+	       (MCTL_DIV2(tCKESR) << 8) | (MCTL_DIV2(tCKE) << 0),
+	       &mctl_ctl->dramtmg[5]);
+
+	/* These timings are relevant for LPDDR2/LPDDR3 only */
+	/* writel((MCTL_TCKDPDE << 24) | (MCTL_TCKDPX << 16) |
+	       (MCTL_TCKCSX << 0), &mctl_ctl->dramtmg[6]); */
+
+	/* printf("DRAMTMG7 reset value: 0x%x\n",
+		readl(&mctl_ctl->dramtmg[7])); */
+	/* DRAMTMG7 reset value: 0x202 */
+	/* DRAMTMG7 should contain t_ckpde and t_ckpdx: check reset values!!! */
+	/* printf("DRAMTMG8 reset value: 0x%x\n",
+		readl(&mctl_ctl->dramtmg[8])); */
+	/* DRAMTMG8 reset value: 0x44 */
+
+	writel((MCTL_DIV32(tXSDLL) << 0), &mctl_ctl->dramtmg[8]);
+
+	writel((MCTL_DIV32(tREFI) << 16) | (MCTL_DIV2(tRFC) << 0),
+	       &mctl_ctl->rfshtmg);
+
+	if (para->dram_type == DRAM_TYPE_DDR3) {
+		writel((2 << 24) | ((MCTL_DIV2(CL) - 2) << 16) |
+		       (1 << 8) | ((MCTL_DIV2(CWL) - 2) << 0),
+			&mctl_ctl->dfitmg[0]);
+	} else {
+		/* TODO */
+	}
+
+	/* TODO: handle the case of the write latency domain going to 0 ... */
+
+	/*
+	 * Disable dfi_init_complete_en (the triggering of the SDRAM
+	 * initialisation when the PHY initialisation completes).
+	 */
+	clrbits_le32(&mctl_ctl->dfimisc, MCTL_DFIMISC_DFI_INIT_COMPLETE_EN);
+	/* Disable the automatic generation of DLL calibration requests */
+	setbits_le32(&mctl_ctl->dfiupd[0], MCTL_DFIUPD0_DIS_AUTO_CTRLUPD);
+
+	/* A80-Q7: 2T, 1 rank, DDR3, full-32bit-DQ */
+	/* TODO: make 2T and BUSWIDTH configurable  */
+	writel(MCTL_MSTR_DEVICETYPE(para->dram_type) |
+	       MCTL_MSTR_BURSTLENGTH(para->dram_type) |
+	       MCTL_MSTR_ACTIVERANKS(para->rank) |
+	       MCTL_MSTR_2TMODE | MCTL_MSTR_BUSWIDTH32,
+	       &mctl_ctl->mstr);
+
+	if (para->dram_type == DRAM_TYPE_DDR3) {
+		writel(MCTL_ZQCTRL0_TZQCL(MCTL_DIV2(tZQoper)) |
+		       (MCTL_DIV2(tZQCS)), &mctl_ctl->zqctrl[0]);
+		/*
+		 * TODO: is the following really necessary as the bottom
+		 * half should already be 0x100 and the upper half should
+		 * be ignored for a DDR3 device???
+		 */
+		writel(MCTL_ZQCTRL1_TZQSI_x1024(0x100),
+		       &mctl_ctl->zqctrl[1]);
+	} else {
+		writel(MCTL_ZQCTRL0_TZQCL(0x200) | MCTL_ZQCTRL0_TZQCS(0x40),
+		       &mctl_ctl->zqctrl[0]);
+		writel(MCTL_ZQCTRL1_TZQRESET(0x28) |
+		       MCTL_ZQCTRL1_TZQSI_x1024(0x100),
+		       &mctl_ctl->zqctrl[1]);
+	}
+
+	/* Assert dfi_init_complete signal */
+	setbits_le32(&mctl_ctl->dfimisc, MCTL_DFIMISC_DFI_INIT_COMPLETE_EN);
+	/* Disable auto-refresh */
+	setbits_le32(&mctl_ctl->rfshctl3, MCTL_RFSHCTL3_DIS_AUTO_REFRESH);
+
+	/* PHY initialisation */
+
+	/* TODO: make 2T and 8-bank mode configurable  */
+	writel(MCTL_PHY_DCR_BYTEMASK | MCTL_PHY_DCR_2TMODE |
+	       MCTL_PHY_DCR_DDR8BNK | MCTL_PHY_DRAMMODE_DDR3,
+	       &mctl_phy->dcr);
+
+	/* For LPDDR2 or LPDDR3, set DQSGX to 0 before training. */
+	if (para->dram_type != DRAM_TYPE_DDR3)
+		clrbits_le32(&mctl_phy->dsgcr, (3 << 6));
+
+	writel(mr[0], &mctl_phy->mr0);
+	writel(mr[1], &mctl_phy->mr1);
+	writel(mr[2], &mctl_phy->mr2);
+	writel(mr[3], &mctl_phy->mr3);
+
+	/*
+	 * The DFI PHY is running at full rate. We thus use the actual
+	 * timings in clock cycles here.
+	 */
+	writel((tRC << 26) | (tRRD << 22) | (tRAS << 16) |
+	       (tRCD << 12) | (tRP << 8) | (tWTR << 4) | (tRTP << 0),
+		&mctl_phy->dtpr[0]);
+	writel((tMRD << 0) | ((tMOD - 12) << 2) | (tFAW << 5) |
+	       (tRFC << 11) | (tWLMRD << 20) | (tWLO << 26),
+	       &mctl_phy->dtpr[1]);
+	writel((tXS << 0) | (MAX(tXP, tXPDLL) << 10) |
+	       (tCKE << 15) | (tDLLK << 19) |
+	       (MCTL_PHY_TRTODT << 29) | (MCTL_PHY_TRTW << 30) |
+	       (((tCCD - 4) & 0x1) << 31),
+	       &mctl_phy->dtpr[2]);
+
+	/* tDQSCK and tDQSCKmax are used LPDDR2/LPDDR3 */
+	/* writel((tDQSCK << 0) | (tDQSCKMAX << 3), &mctl_phy->dtpr[3]); */
+
+	/*
+	 * We use the same values used by Allwinner's Boot0 for the PTR
+	 * (PHY timing register) configuration that is tied to the PHY
+	 * implementation.
+	 */
+	writel(0x42C21590, &mctl_phy->ptr[0]);
+	writel(0xD05612C0, &mctl_phy->ptr[1]);
+	if (para->dram_type == DRAM_TYPE_DDR3) {
+		const unsigned int tdinit0 = 500 * CONFIG_DRAM_CLK; /* 500us */
+		const unsigned int tdinit1 = (360 * CONFIG_DRAM_CLK + 999) /
+			1000; /* 360ns */
+		const unsigned int tdinit2 = 200 * CONFIG_DRAM_CLK; /* 200us */
+		const unsigned int tdinit3 = CONFIG_DRAM_CLK; /* 1us */
+
+		writel((tdinit1 << 20) | tdinit0, &mctl_phy->ptr[3]);
+		writel((tdinit3 << 18) | tdinit2, &mctl_phy->ptr[4]);
+	} else {
+		/* LPDDR2 or LPDDR3 */
+		const unsigned int tdinit0 = (100 * CONFIG_DRAM_CLK + 999) /
+			1000; /* 100ns */
+		const unsigned int tdinit1 = 200 * CONFIG_DRAM_CLK; /* 200us */
+		const unsigned int tdinit2 = 22 * CONFIG_DRAM_CLK; /* 11us */
+		const unsigned int tdinit3 = 2 * CONFIG_DRAM_CLK; /* 2us */
+
+		writel((tdinit1 << 20) | tdinit0, &mctl_phy->ptr[3]);
+		writel((tdinit3 << 18) | tdinit2, &mctl_phy->ptr[4]);
+	}
+
+	/* TEST ME */
+	writel(0x00203131, &mctl_phy->acmdlr);
+
+	/* TODO: can we enable this for 2 ranks, even when we don't know yet */
+	writel(MCTL_DTCR_DEFAULT | MCTL_DTCR_RANKEN(para->rank),
+	       &mctl_phy->dtcr);
+
+	/* TODO: half width */
+	debug("DX2GCR0 reset: 0x%x\n", readl(&mctl_phy->dx[2].gcr[0]));
+	writel(0x7C000285, &mctl_phy->dx[2].gcr[0]);
+	writel(0x7C000285, &mctl_phy->dx[3].gcr[0]);
+
+	clrsetbits_le32(&mctl_phy->zq[0].pr, 0xff,
+			(CONFIG_DRAM_ZQ >>  0) & 0xff);  /* CK/CA */
+	clrsetbits_le32(&mctl_phy->zq[1].pr, 0xff,
+			(CONFIG_DRAM_ZQ >>  8) & 0xff);  /* DX0/DX1 */
+	clrsetbits_le32(&mctl_phy->zq[2].pr, 0xff,
+			(CONFIG_DRAM_ZQ >> 16) & 0xff);  /* DX2/DX3 */
+
+	/* TODO: make configurable & implement non-ODT path */
+	if (1) {
+		int lane;
+		for (lane = 0; lane < 4; ++lane) {
+			clrbits_le32(&mctl_phy->dx[lane].gcr[2], 0xffff);
+			clrbits_le32(&mctl_phy->dx[lane].gcr[3],
+				     (0x3<<12) | (0x3<<4));
+		}
+	} else {
+		/* TODO: check */
+		int lane;
+		for (lane = 0; lane < 4; ++lane) {
+			clrsetbits_le32(&mctl_phy->dx[lane].gcr[2], 0xffff,
+					0xaaaa);
+			if (para->dram_type == DRAM_TYPE_DDR3)
+				setbits_le32(&mctl_phy->dx[lane].gcr[3],
+					     (0x3<<12) | (0x3<<4));
+			else
+				setbits_le32(&mctl_phy->dx[lane].gcr[3],
+					     0x00000012);
+		}
+	}
+
+	writel(0x04058D02, &mctl_phy->zq[0].cr); /* CK/CA */
+	writel(0x04058D02, &mctl_phy->zq[1].cr); /* DX0/DX1 */
+	writel(0x04058D02, &mctl_phy->zq[2].cr); /* DX2/DX3 */
+
+	/* Disable auto-refresh prior to data training */
+	setbits_le32(&mctl_ctl->rfshctl3, MCTL_RFSHCTL3_DIS_AUTO_REFRESH);
+
+	setbits_le32(&mctl_phy->dsgcr, 0xf << 24); /* unclear what this is... */
+	/* TODO: IODDRM (IO DDR-MODE) for DDR3L */
+	clrsetbits_le32(&mctl_phy->pgcr[1],
+			MCTL_PGCR1_ZCKSEL_MASK,
+			MCTL_PGCR1_IODDRM_DDR3 | MCTL_PGCR1_INHVT_EN);
+
+	setbits_le32(&mctl_phy->pllcr, 0x3 << 19); /* PLL frequency select */
+	/* TODO: single-channel PLL mode??? missing */
+	setbits_le32(&mctl_phy->pllcr,
+		     MCTL_PLLGCR_PLL_BYPASS | MCTL_PLLGCR_PLL_POWERDOWN);
+	/* setbits_le32(&mctl_phy->pir, MCTL_PIR_PLL_BYPASS); included below */
+
+	/* Disable VT compensation */
+	clrbits_le32(&mctl_phy->pgcr[0], 0x3f);
+
+	/* TODO: "other" PLL mode ... 0x20000 seems to be the PLL Bypass */
+	if (para->dram_type == DRAM_TYPE_DDR3)
+		clrsetbits_le32(&mctl_phy->pir, MCTL_PIR_MASK, 0x20df3);
+	else
+		clrsetbits_le32(&mctl_phy->pir, MCTL_PIR_MASK, 0x2c573);
+
+	sdelay(10000); /* XXX necessary? */
+
+	/* Wait for the INIT bit to clear itself... */
+	while ((readl(&mctl_phy->pir) & MCTL_PIR_INIT) != MCTL_PIR_INIT) {
+		/* not done yet -- keep spinning */
+		debug("MCTL_PIR_INIT not set\n");
+		sdelay(1000);
+		/* TODO: implement timeout */
+	}
+
+	/* TODO: not used --- there's a "2rank debug" section here */
+
+	/* Original dram init code which may come in handy later
+	********************************************************
+	 * LPDDR2 and LPDDR3 *
+	if ((para->dram_type) == 6 || (para->dram_type) == 7) {
+		reg_val = mctl_read_w(P0_DSGCR + ch_offset);
+		reg_val &= (~(0x3<<6));		* set DQSGX to 1 *
+		reg_val |= (0x1<<6);		* dqs gate extend *
+		mctl_write_w(P0_DSGCR + ch_offset, reg_val);
+		dram_dbg("DQS Gate Extend Enable!\n", ch_index);
+	}
+
+	 * Disable ZCAL after initial--for nand dma debug--20140330 by YSZ *
+	if (para->dram_tpr13 & (0x1<<31)) {
+		reg_val = mctl_read_w(P0_ZQ0CR + ch_offset);
+		reg_val |= (0x7<<11);
+		mctl_write_w(P0_ZQ0CR + ch_offset, reg_val);
+	}
+	********************************************************
+	*/
+
+	/*
+	 * TODO: more 2-rank support
+	 * (setting the "dqs gate delay to average between 2 rank")
+	 */
+
+	/* check if any errors are set */
+	if (readl(&mctl_phy->pgsr[0]) & MCTL_PGSR0_ERRORS) {
+		debug("Channel %d unavailable!\n", ch_index);
+		return 0;
+	} else{
+		/* initial OK */
+		debug("Channel %d OK!\n", ch_index);
+		/* return 1; */
+	}
+
+	while ((readl(&mctl_ctl->stat) & 0x1) != 0x1) {
+		debug("Waiting for INIT to be done (controller to come up into 'normal operating' mode\n");
+		sdelay(100000);
+		/* init not done */
+		/* TODO: implement time-out */
+	}
+	debug("done\n");
+
+	/* "DDR is controller by contoller" */
+	clrbits_le32(&mctl_phy->pgcr[3], (1 << 25));
+
+	/* TODO: is the following necessary? */
+	debug("DFIMISC before writing 0: 0x%x\n", readl(&mctl_ctl->dfimisc));
+	writel(0, &mctl_ctl->dfimisc);
+
+	/* Enable auto-refresh */
+	clrbits_le32(&mctl_ctl->rfshctl3, MCTL_RFSHCTL3_DIS_AUTO_REFRESH);
+
+	debug("channel_init complete\n");
+	return 1;
+}
+
+signed int DRAMC_get_dram_size(void)
+{
+	struct sunxi_mctl_com_reg * const mctl_com =
+		(struct sunxi_mctl_com_reg *)SUNXI_DRAM_COM_BASE;
+
+	unsigned int reg_val;
+	unsigned int dram_size;
+	unsigned int temp;
+
+	reg_val = readl(&mctl_com->cr);
+
+	temp = (reg_val >> 8) & 0xf;	/* page size code */
+	dram_size = (temp - 6);		/* (1 << dram_size) * 512Bytes */
+
+	temp = (reg_val >> 4) & 0xf;	/* row width code */
+	dram_size += (temp + 1);	/* (1 << dram_size) * 512Bytes */
+
+	temp = (reg_val >> 2) & 0x3;	/* bank number code */
+	dram_size += (temp + 2);	/* (1 << dram_size) * 512Bytes */
+
+	temp = reg_val & 0x3;		/* rank number code */
+	dram_size += temp;		/* (1 << dram_size) * 512Bytes */
+
+	temp = (reg_val >> 19) & 0x1;	/* channel number code */
+	dram_size += temp;		/* (1 << dram_size) * 512Bytes */
+
+	dram_size = dram_size - 11;	/* (1 << dram_size) MBytes */
+
+	return 1 << dram_size;
+}
+
+unsigned long sunxi_dram_init(void)
+{
+	struct sunxi_mctl_com_reg * const mctl_com =
+		(struct sunxi_mctl_com_reg *)SUNXI_DRAM_COM_BASE;
+
+	struct dram_sun9i_cl_cwl_timing cl_cwl[] = {
+		{ .CL =  5, .CWL = 5, .tCKmin = 3000, .tCKmax = 3300 },
+		{ .CL =  6, .CWL = 5, .tCKmin = 2500, .tCKmax = 3300 },
+		{ .CL =  8, .CWL = 6, .tCKmin = 1875, .tCKmax = 2500 },
+		{ .CL = 10, .CWL = 7, .tCKmin = 1500, .tCKmax = 1875 },
+		{ .CL = 11, .CWL = 8, .tCKmin = 1250, .tCKmax = 1500 }
+	};
+
+	/* Set initial parameters, these get modified by the autodetect code */
+	struct dram_sun9i_para para = {
+		.dram_type = DRAM_TYPE_DDR3,
+		.bus_width = 32,
+		.chan = 2,
+		.rank = 1,
+		/* .rank = 2, */
+		.page_size = 4096,
+		/* .rows = 16, */
+		.rows = 15,
+
+		/* CL/CWL table for the speed bin */
+		.cl_cwl_table = cl_cwl,
+		.cl_cwl_numentries = sizeof(cl_cwl) /
+			sizeof(struct dram_sun9i_cl_cwl_timing),
+
+		/* timings */
+		.tREFI = 7800,	/* 7.8us (up to 85 degC) */
+		.tRFC  = 260,	/* 260ns for 4GBit devices */
+				/* 350ns @ 8GBit */
+
+		.tRCD  = 13750,
+		.tRP   = 13750,
+		.tRC   = 48750,
+		.tRAS  = 35000,
+
+		.tDLLK = 512,
+		.tRTP  = { .ck = 4, .ps = 7500 },
+		.tWTR  = { .ck = 4, .ps = 7500 },
+		.tWR   = 15,
+		.tMRD  = 4,
+		.tMOD  = { .ck = 12, .ps = 15000 },
+		.tCCD  = 4,
+		.tRRD  = { .ck = 4, .ps = 7500 },
+		.tFAW  = 40,
+
+		/* calibration timing */
+		/* .tZQinit = { .ck = 512, .ps = 640000 }, */
+		.tZQoper = { .ck = 256, .ps = 320000 },
+		.tZQCS   = { .ck = 64,  .ps = 80000 },
+
+		/* reset timing */
+		/* .tXPR  = { .ck = 5, .ps = 10000 }, */
+
+		/* self-refresh timings */
+		.tXS  = { .ck = 5, .ps = 10000 },
+		.tXSDLL = 512,
+		.tCKSRE = { .ck = 5, .ps = 10000 },
+		.tCKSRX = { .ck = 5, .ps = 10000 },
+
+		/* power-down timings */
+		.tXP = { .ck = 3, .ps = 6000 },
+		.tXPDLL = { .ck = 10, .ps = 24000 },
+		.tCKE = { .ck = 3, .ps = 5000 },
+
+		/* write leveling timings */
+		.tWLMRD = 40,
+		/* .tWLDQSEN = 25, */
+		.tWLO = 7500,
+		/* .tWLOE = 2000, */
+	};
+
+	/*
+	 * Disable A80 internal 240 ohm resistor.
+	 *
+	 * This code sequence is adapated from Allwinner's Boot0 (see
+	 * https://github.com/allwinner-zh/bootloader.git), as there
+	 * is no documentation for these two registers in the R_PRCM
+	 * block.
+	 */
+	setbits_le32(SUNXI_PRCM_BASE + 0x1e0, (0x3 << 8));
+	writel(0, SUNXI_PRCM_BASE + 0x1e8);
+
+	mctl_sys_init();
+
+	if (!mctl_channel_init(0, &para))
+		return 0;
+
+	/* dual-channel */
+	if (!mctl_channel_init(1, &para)) {
+		/* disable channel 1 */
+		clrsetbits_le32(&mctl_com->cr, MCTL_CR_CHANNEL_MASK,
+				MCTL_CR_CHANNEL_SINGLE);
+		/* disable channel 1 global clock */
+		clrbits_le32(&mctl_com->cr, MCTL_CCR_CH1_CLK_EN);
+	}
+
+	mctl_com_init(&para);
+
+	/* return the proper RAM size */
+	return DRAMC_get_dram_size() << 20;
+}
diff --git a/board/sunxi/Kconfig b/board/sunxi/Kconfig
index c0ffeb3333..a126c3e301 100644
--- a/board/sunxi/Kconfig
+++ b/board/sunxi/Kconfig
@@ -141,11 +141,13 @@ config DRAM_TYPE
 
 config DRAM_CLK
 	int "sunxi dram clock speed"
+	default 792 if MACH_SUN9I
 	default 312 if MACH_SUN6I || MACH_SUN8I
 	default 360 if MACH_SUN4I || MACH_SUN5I || MACH_SUN7I
 	---help---
-	Set the dram clock speed, valid range 240 - 480, must be a multiple
-	of 24.
+	Set the dram clock speed, valid range 240 - 480 (prior to sun9i),
+	must be a multiple of 24. For the sun9i (A80), the tested values
+	(for DDR3-1600) are 312 to 792.
 
 if MACH_SUN5I || MACH_SUN7I
 config DRAM_MBUS_CLK