sunxi: Add H616 DRAM support

Allwinner H616 supports many types of DRAM. Most notably it supports
LPDDR4. However, all commercially available boards at this time use
only DDR3, so this commit adds only DDR3 support.

Controller and MBUS are very similar to H6 but PHY is completely
unknown.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Acked-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>

arch/arm/include/asm/arch-sunxi/dram.h

@@ -29,6 +29,8 @@
 #include <asm/arch/dram_sun9i.h>
 #elif defined(CONFIG_MACH_SUN50I_H6)
 #include <asm/arch/dram_sun50i_h6.h>
+#elif defined(CONFIG_MACH_SUN50I_H616)
+#include <asm/arch/dram_sun50i_h616.h>
 #else
 #include <asm/arch/dram_sun4i.h>
 #endif

arch/arm/include/asm/arch-sunxi/dram_sun50i_h616.h

@@ -0,0 +1,159 @@
+/*
+ * H616 dram controller register and constant defines
+ *
+ * (C) Copyright 2020  Jernej Skrabec <jernej.skrabec@siol.net>
+ *
+ * Based on H6 one, which is:
+ * (C) Copyright 2017  Icenowy Zheng <icenowy@aosc.io>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#ifndef _SUNXI_DRAM_SUN50I_H616_H
+#define _SUNXI_DRAM_SUN50I_H616_H
+
+#include <stdbool.h>
+#ifndef __ASSEMBLY__
+#include <linux/bitops.h>
+#endif
+
+enum sunxi_dram_type {
+	SUNXI_DRAM_TYPE_DDR3 = 3,
+	SUNXI_DRAM_TYPE_DDR4,
+	SUNXI_DRAM_TYPE_LPDDR3 = 7,
+	SUNXI_DRAM_TYPE_LPDDR4
+};
+
+/* MBUS part is largely the same as in H6, except for one special register */
+struct sunxi_mctl_com_reg {
+	u32 cr;			/* 0x000 control register */
+	u8 reserved_0x004[4];	/* 0x004 */
+	u32 unk_0x008;		/* 0x008 */
+	u32 tmr;		/* 0x00c timer register */
+	u8 reserved_0x010[4];	/* 0x010 */
+	u32 unk_0x014;		/* 0x014 */
+	u8 reserved_0x018[8];	/* 0x018 */
+	u32 maer0;		/* 0x020 master enable register 0 */
+	u32 maer1;		/* 0x024 master enable register 1 */
+	u32 maer2;		/* 0x028 master enable register 2 */
+	u8 reserved_0x02c[468];	/* 0x02c */
+	u32 bwcr;		/* 0x200 bandwidth control register */
+	u8 reserved_0x204[12];	/* 0x204 */
+	/*
+	 * The last master configured by BSP libdram is at 0x49x, so the
+	 * size of this struct array is set to 41 (0x29) now.
+	 */
+	struct {
+		u32 cfg0;		/* 0x0 */
+		u32 cfg1;		/* 0x4 */
+		u8 reserved_0x8[8];	/* 0x8 */
+	} master[41];		/* 0x210 + index * 0x10 */
+	u8 reserved_0x4a0[96];	/* 0x4a0 */
+	u32 unk_0x500;		/* 0x500 */
+};
+check_member(sunxi_mctl_com_reg, unk_0x500, 0x500);
+
+/*
+ * Controller registers seems to be the same or at least very similar
+ * to those in H6.
+ */
+struct sunxi_mctl_ctl_reg {
+	u32 mstr;		/* 0x000 */
+	u32 statr;		/* 0x004 unused */
+	u32 mstr1;		/* 0x008 unused */
+	u32 clken;		/* 0x00c */
+	u32 mrctrl0;		/* 0x010 unused */
+	u32 mrctrl1;		/* 0x014 unused */
+	u32 mrstatr;		/* 0x018 unused */
+	u32 mrctrl2;		/* 0x01c unused */
+	u32 derateen;		/* 0x020 unused */
+	u32 derateint;		/* 0x024 unused */
+	u8 reserved_0x028[8];	/* 0x028 */
+	u32 pwrctl;		/* 0x030 unused */
+	u32 pwrtmg;		/* 0x034 unused */
+	u32 hwlpctl;		/* 0x038 unused */
+	u8 reserved_0x03c[20];	/* 0x03c */
+	u32 rfshctl0;		/* 0x050 unused */
+	u32 rfshctl1;		/* 0x054 unused */
+	u8 reserved_0x058[8];	/* 0x05c */
+	u32 rfshctl3;		/* 0x060 */
+	u32 rfshtmg;		/* 0x064 */
+	u8 reserved_0x068[104];	/* 0x068 */
+	u32 init[8];		/* 0x0d0 */
+	u32 dimmctl;		/* 0x0f0 unused */
+	u32 rankctl;		/* 0x0f4 */
+	u8 reserved_0x0f8[8];	/* 0x0f8 */
+	u32 dramtmg[17];	/* 0x100 */
+	u8 reserved_0x144[60];	/* 0x144 */
+	u32 zqctl[3];		/* 0x180 */
+	u32 zqstat;		/* 0x18c unused */
+	u32 dfitmg0;		/* 0x190 */
+	u32 dfitmg1;		/* 0x194 */
+	u32 dfilpcfg[2];	/* 0x198 unused */
+	u32 dfiupd[3];		/* 0x1a0 */
+	u32 reserved_0x1ac;	/* 0x1ac */
+	u32 dfimisc;		/* 0x1b0 */
+	u32 dfitmg2;		/* 0x1b4 unused */
+	u32 dfitmg3;		/* 0x1b8 unused */
+	u32 dfistat;		/* 0x1bc */
+	u32 dbictl;		/* 0x1c0 */
+	u8 reserved_0x1c4[60];	/* 0x1c4 */
+	u32 addrmap[12];	/* 0x200 */
+	u8 reserved_0x230[16];	/* 0x230 */
+	u32 odtcfg;		/* 0x240 */
+	u32 odtmap;		/* 0x244 */
+	u8 reserved_0x248[8];	/* 0x248 */
+	u32 sched[2];		/* 0x250 */
+	u8 reserved_0x258[180];	/* 0x258 */
+	u32 dbgcmd;		/* 0x30c unused */
+	u32 dbgstat;		/* 0x310 unused */
+	u8 reserved_0x314[12];	/* 0x314 */
+	u32 swctl;		/* 0x320 */
+	u32 swstat;		/* 0x324 */
+	u8 reserved_0x328[7768];/* 0x328 */
+	u32 unk_0x2180;		/* 0x2180 */
+	u8 reserved_0x2184[188];/* 0x2184 */
+	u32 unk_0x2240;		/* 0x2240 */
+	u8 reserved_0x2244[3900];/* 0x2244 */
+	u32 unk_0x3180;		/* 0x3180 */
+	u8 reserved_0x3184[188];/* 0x3184 */
+	u32 unk_0x3240;		/* 0x3240 */
+	u8 reserved_0x3244[3900];/* 0x3244 */
+	u32 unk_0x4180;		/* 0x4180 */
+	u8 reserved_0x4184[188];/* 0x4184 */
+	u32 unk_0x4240;		/* 0x4240 */
+};
+check_member(sunxi_mctl_ctl_reg, swstat, 0x324);
+check_member(sunxi_mctl_ctl_reg, unk_0x4240, 0x4240);
+
+#define MSTR_DEVICETYPE_DDR3	BIT(0)
+#define MSTR_DEVICETYPE_LPDDR2	BIT(2)
+#define MSTR_DEVICETYPE_LPDDR3	BIT(3)
+#define MSTR_DEVICETYPE_DDR4	BIT(4)
+#define MSTR_DEVICETYPE_MASK	GENMASK(5, 0)
+#define MSTR_2TMODE		BIT(10)
+#define MSTR_BUSWIDTH_FULL	(0 << 12)
+#define MSTR_BUSWIDTH_HALF	(1 << 12)
+#define MSTR_ACTIVE_RANKS(x)	(((x == 2) ? 3 : 1) << 24)
+#define MSTR_BURST_LENGTH(x)	(((x) >> 1) << 16)
+
+struct dram_para {
+	u32 clk;
+	enum sunxi_dram_type type;
+	u8 cols;
+	u8 rows;
+	u8 ranks;
+	u8 bus_full_width;
+};
+
+
+static inline int ns_to_t(int nanoseconds)
+{
+	const unsigned int ctrl_freq = CONFIG_DRAM_CLK / 2;
+
+	return DIV_ROUND_UP(ctrl_freq * nanoseconds, 1000);
+}
+
+void mctl_set_timing_params(struct dram_para *para);
+
+#endif /* _SUNXI_DRAM_SUN50I_H616_H */

arch/arm/mach-sunxi/Kconfig

@@ -48,6 +48,46 @@ config DRAM_SUN50I_H6
 	  Select this dram controller driver for some sun50i platforms,
 	  like H6.
 
+config DRAM_SUN50I_H616
+	bool
+	help
+	  Select this dram controller driver for some sun50i platforms,
+	  like H616.
+
+if DRAM_SUN50I_H616
+config DRAM_SUN50I_H616_WRITE_LEVELING
+	bool "H616 DRAM write leveling"
+	---help---
+	  Select this when DRAM on your H616 board needs write leveling.
+
+config DRAM_SUN50I_H616_READ_CALIBRATION
+	bool "H616 DRAM read calibration"
+	---help---
+	  Select this when DRAM on your H616 board needs read calibration.
+
+config DRAM_SUN50I_H616_READ_TRAINING
+	bool "H616 DRAM read training"
+	---help---
+	  Select this when DRAM on your H616 board needs read training.
+
+config DRAM_SUN50I_H616_WRITE_TRAINING
+	bool "H616 DRAM write training"
+	---help---
+	  Select this when DRAM on your H616 board needs write training.
+
+config DRAM_SUN50I_H616_BIT_DELAY_COMPENSATION
+	bool "H616 DRAM bit delay compensation"
+	---help---
+	  Select this when DRAM on your H616 board needs bit delay
+	  compensation.
+
+config DRAM_SUN50I_H616_UNKNOWN_FEATURE
+	bool "H616 DRAM unknown feature"
+	---help---
+	  Select this when DRAM on your H616 board needs this unknown
+	  feature.
+endif
+
 config SUN6I_P2WI
 	bool "Allwinner sun6i internal P2WI controller"
 	help
@@ -424,6 +464,7 @@ config DRAM_CLK
 		       MACH_SUN8I_V3S
 	default 672 if MACH_SUN50I
 	default 744 if MACH_SUN50I_H6
+	default 720 if MACH_SUN50I_H616
 	---help---
 	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
@@ -440,6 +481,7 @@ endif
 
 config DRAM_ZQ
 	int "sunxi dram zq value"
+	depends on !MACH_SUN50I_H616
 	default 123 if MACH_SUN4I || MACH_SUN5I || MACH_SUN6I || \
 		       MACH_SUN8I_A23 || MACH_SUN8I_A33 || MACH_SUN8I_A83T
 	default 127 if MACH_SUN7I
@@ -457,6 +499,7 @@ config DRAM_ODT_EN
 	default y if MACH_SUN8I_R40
 	default y if MACH_SUN50I
 	default y if MACH_SUN50I_H6
+	default y if MACH_SUN50I_H616
 	---help---
 	Select this to enable dram odt (on die termination).
 

arch/arm/mach-sunxi/Makefile

@@ -40,4 +40,6 @@ obj-$(CONFIG_SUNXI_DRAM_DW)	+= dram_sunxi_dw.o
 obj-$(CONFIG_SUNXI_DRAM_DW)	+= dram_timings/
 obj-$(CONFIG_DRAM_SUN50I_H6)	+= dram_sun50i_h6.o
 obj-$(CONFIG_DRAM_SUN50I_H6)	+= dram_timings/
+obj-$(CONFIG_DRAM_SUN50I_H616)	+= dram_sun50i_h616.o
+obj-$(CONFIG_DRAM_SUN50I_H616)	+= dram_timings/
 endif

arch/arm/mach-sunxi/dram_timings/Makefile

@@ -3,3 +3,5 @@ obj-$(CONFIG_SUNXI_DRAM_LPDDR3_STOCK)	+= lpddr3_stock.o
 obj-$(CONFIG_SUNXI_DRAM_DDR2_V3S)	+= ddr2_v3s.o
 obj-$(CONFIG_SUNXI_DRAM_H6_LPDDR3)	+= h6_lpddr3.o
 obj-$(CONFIG_SUNXI_DRAM_H6_DDR3_1333)	+= h6_ddr3_1333.o
+# currently only DDR3 is supported on H616
+obj-$(CONFIG_MACH_SUN50I_H616)		+= h616_ddr3_1333.o

arch/arm/mach-sunxi/dram_timings/h616_ddr3_1333.c

@@ -0,0 +1,94 @@
+/*
+ * sun50i H616 DDR3-1333 timings, as programmed by Allwinner's boot0
+ *
+ * The chips are probably able to be driven by a faster clock, but boot0
+ * uses a more conservative timing (as usual).
+ *
+ * (C) Copyright 2020 Jernej Skrabec <jernej.skrabec@siol.net>
+ * Based on H6 DDR3 timings:
+ * (C) Copyright 2018,2019 Arm Ltd.
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <asm/arch/dram.h>
+#include <asm/arch/cpu.h>
+
+void mctl_set_timing_params(struct dram_para *para)
+{
+	struct sunxi_mctl_ctl_reg * const mctl_ctl =
+			(struct sunxi_mctl_ctl_reg *)SUNXI_DRAM_CTL0_BASE;
+
+	u8 tccd		= 2;			/* JEDEC: 4nCK */
+	u8 tfaw		= ns_to_t(50);		/* JEDEC: 30 ns w/ 1K pages */
+	u8 trrd		= max(ns_to_t(6), 4);	/* JEDEC: max(6 ns, 4nCK) */
+	u8 trcd		= ns_to_t(15);		/* JEDEC: 13.5 ns */
+	u8 trc		= ns_to_t(53);		/* JEDEC: 49.5 ns */
+	u8 txp		= max(ns_to_t(6), 3);	/* JEDEC: max(6 ns, 3nCK) */
+	u8 trtp		= max(ns_to_t(8), 2);	/* JEDEC: max(7.5 ns, 4nCK) */
+	u8 trp		= ns_to_t(15);		/* JEDEC: >= 13.75 ns */
+	u8 tras		= ns_to_t(38);		/* JEDEC >= 36 ns, <= 9*trefi */
+	u16 trefi	= ns_to_t(7800) / 32;	/* JEDEC: 7.8us@Tcase <= 85C */
+	u16 trfc	= ns_to_t(350);		/* JEDEC: 160 ns for 2Gb */
+	u16 txsr	= 4;			/* ? */
+
+	u8 tmrw		= 0;			/* ? */
+	u8 tmrd		= 4;			/* JEDEC: 4nCK */
+	u8 tmod		= max(ns_to_t(15), 12);	/* JEDEC: max(15 ns, 12nCK) */
+	u8 tcke		= max(ns_to_t(6), 3);	/* JEDEC: max(5.625 ns, 3nCK) */
+	u8 tcksrx	= max(ns_to_t(10), 4);	/* JEDEC: max(10 ns, 5nCK) */
+	u8 tcksre	= max(ns_to_t(10), 4);	/* JEDEC: max(10 ns, 5nCK) */
+	u8 tckesr	= tcke + 1;		/* JEDEC: tCKE(min) + 1nCK */
+	u8 trasmax	= (para->clk / 2) / 15;	/* JEDEC: tREFI * 9 */
+	u8 txs		= ns_to_t(360) / 32;	/* JEDEC: max(5nCK,tRFC+10ns) */
+	u8 txsdll	= 16;			/* JEDEC: 512 nCK */
+	u8 txsabort	= 4;			/* ? */
+	u8 txsfast	= 4;			/* ? */
+	u8 tcl		= 7;			/* JEDEC: CL / 2 => 6 */
+	u8 tcwl		= 5;			/* JEDEC: 8 */
+	u8 t_rdata_en	= 9;			/* ? */
+
+	u8 twtp		= 14;			/* (WL + BL / 2 + tWR) / 2 */
+	u8 twr2rd	= trtp + 7;		/* (WL + BL / 2 + tWTR) / 2 */
+	u8 trd2wr	= 5;			/* (RL + BL / 2 + 2 - WL) / 2 */
+
+	/* set DRAM timing */
+	writel((twtp << 24) | (tfaw << 16) | (trasmax << 8) | tras,
+	       &mctl_ctl->dramtmg[0]);
+	writel((txp << 16) | (trtp << 8) | trc, &mctl_ctl->dramtmg[1]);
+	writel((tcwl << 24) | (tcl << 16) | (trd2wr << 8) | twr2rd,
+	       &mctl_ctl->dramtmg[2]);
+	writel((tmrw << 20) | (tmrd << 12) | tmod, &mctl_ctl->dramtmg[3]);
+	writel((trcd << 24) | (tccd << 16) | (trrd << 8) | trp,
+	       &mctl_ctl->dramtmg[4]);
+	writel((tcksrx << 24) | (tcksre << 16) | (tckesr << 8) | tcke,
+	       &mctl_ctl->dramtmg[5]);
+	/* Value suggested by ZynqMP manual and used by libdram */
+	writel((txp + 2) | 0x02020000, &mctl_ctl->dramtmg[6]);
+	writel((txsfast << 24) | (txsabort << 16) | (txsdll << 8) | txs,
+	       &mctl_ctl->dramtmg[8]);
+	writel(0x00020208, &mctl_ctl->dramtmg[9]);
+	writel(0xE0C05, &mctl_ctl->dramtmg[10]);
+	writel(0x440C021C, &mctl_ctl->dramtmg[11]);
+	writel(8, &mctl_ctl->dramtmg[12]);
+	writel(0xA100002, &mctl_ctl->dramtmg[13]);
+	writel(txsr, &mctl_ctl->dramtmg[14]);
+
+	clrbits_le32(&mctl_ctl->init[0], 3 << 30);
+	writel(0x420000, &mctl_ctl->init[1]);
+	writel(5, &mctl_ctl->init[2]);
+	writel(0x1f140004, &mctl_ctl->init[3]);
+	writel(0x00200000, &mctl_ctl->init[4]);
+
+	writel(0, &mctl_ctl->dfimisc);
+	clrsetbits_le32(&mctl_ctl->rankctl, 0xff0, 0x660);
+
+	/* Configure DFI timing */
+	writel((tcl - 2) | 0x2000000 | (t_rdata_en << 16) | 0x808000,
+	       &mctl_ctl->dfitmg0);
+	writel(0x100202, &mctl_ctl->dfitmg1);
+
+	/* set refresh timing */
+	writel((trefi << 16) | trfc, &mctl_ctl->rfshtmg);
+}