diff --git a/Kconfig b/Kconfig
index 520679f57e..990353800f 100644
--- a/Kconfig
+++ b/Kconfig
@@ -200,7 +200,7 @@ config SYS_MALLOC_F_LEN
 	default 0x2000 if (ARCH_IMX8 || ARCH_IMX8M || ARCH_MX7 || \
 			   ARCH_MX7ULP || ARCH_MX6 || ARCH_MX5 || \
 			   ARCH_LS1012A || ARCH_LS1021A || ARCH_LS1043A || \
-			   ARCH_LS1046A || ARCH_QEMU)
+			   ARCH_LS1046A || ARCH_QEMU || ARCH_SUNXI)
 	default 0x400
 	help
 	  Before relocation, memory is very limited on many platforms. Still,
diff --git a/Makefile b/Makefile
index cb28cf6aa0..e08cd751e0 100644
--- a/Makefile
+++ b/Makefile
@@ -1332,6 +1332,7 @@ cmd_binman = $(srctree)/tools/binman/binman $(if $(BINMAN_DEBUG),-D) \
 		-I arch/$(ARCH)/dts -a of-list=$(CONFIG_OF_LIST) \
 		-a atf-bl31-path=${BL31} \
 		-a default-dt=$(default_dt) \
+		-a scp-path=$(SCP) \
 		$(BINMAN_$(@F))
 
 OBJCOPYFLAGS_u-boot.ldr.hex := -I binary -O ihex
@@ -1441,11 +1442,13 @@ else
 MKIMAGEFLAGS_u-boot.itb = -E
 endif
 
+ifdef U_BOOT_ITS
 u-boot.itb: u-boot-nodtb.bin \
 		$(if $(CONFIG_OF_SEPARATE)$(CONFIG_OF_EMBED)$(CONFIG_OF_HOSTFILE),dts/dt.dtb) \
 		$(U_BOOT_ITS) FORCE
 	$(call if_changed,mkfitimage)
 	$(BOARD_SIZE_CHECK)
+endif
 
 u-boot-spl.kwb: u-boot.img spl/u-boot-spl.bin FORCE
 	$(call if_changed,mkimage)
diff --git a/arch/arm/dts/sunxi-u-boot.dtsi b/arch/arm/dts/sunxi-u-boot.dtsi
index c97943b3c1..c77cf7cacf 100644
--- a/arch/arm/dts/sunxi-u-boot.dtsi
+++ b/arch/arm/dts/sunxi-u-boot.dtsi
@@ -1,5 +1,13 @@
 #include <config.h>
 
+#ifdef CONFIG_MACH_SUN50I_H6
+#define BL31_ADDR 0x104000
+#define  SCP_ADDR 0x114000
+#else
+#define BL31_ADDR  0x44000
+#define  SCP_ADDR  0x50000
+#endif
+
 / {
 	aliases {
 		mmc1 = &mmc2;
@@ -14,9 +22,11 @@
 	u-boot-sunxi-with-spl {
 		filename = "u-boot-sunxi-with-spl.bin";
 		pad-byte = <0xff>;
+
 		blob {
 			filename = "spl/sunxi-spl.bin";
 		};
+
 #ifdef CONFIG_ARM64
 		fit {
 			description = "Configuration to load ATF before U-Boot";
@@ -27,6 +37,7 @@
 				uboot {
 					description = "U-Boot (64-bit)";
 					type = "standalone";
+					os = "u-boot";
 					arch = "arm64";
 					compression = "none";
 					load = <0x4a000000>;
@@ -34,24 +45,35 @@
 					u-boot-nodtb {
 					};
 				};
+
 				atf {
 					description = "ARM Trusted Firmware";
 					type = "firmware";
+					os = "arm-trusted-firmware";
 					arch = "arm64";
 					compression = "none";
-/* TODO: Do this with an overwrite in this board's dtb? */
-#ifdef CONFIG_MACH_SUN50I_H6
-					load = <0x104000>;
-					entry = <0x104000>;
-#else
-					load = <0x44000>;
-					entry = <0x44000>;
-#endif
+					load = <BL31_ADDR>;
+					entry = <BL31_ADDR>;
+
 					atf-bl31 {
+						filename = "bl31.bin";
 						missing-msg = "atf-bl31-sunxi";
 					};
 				};
 
+				scp {
+					description = "SCP firmware";
+					type = "firmware";
+					arch = "or1k";
+					compression = "none";
+					load = <SCP_ADDR>;
+
+					scp {
+						filename = "scp.bin";
+						missing-msg = "scp-sunxi";
+					};
+				};
+
 				@fdt-SEQ {
 					description = "NAME";
 					type = "flat_dt";
@@ -61,10 +83,11 @@
 
 			configurations {
 				default = "config-1";
+
 				@config-SEQ {
 					description = "NAME";
-					firmware = "uboot";
-					loadables = "atf";
+					firmware = "atf";
+					loadables = "scp", "uboot";
 					fdt = "fdt-SEQ";
 				};
 			};
diff --git a/arch/arm/include/asm/arch-sunxi/cpu.h b/arch/arm/include/asm/arch-sunxi/cpu.h
index 4c399b0a15..8b57d24e2f 100644
--- a/arch/arm/include/asm/arch-sunxi/cpu.h
+++ b/arch/arm/include/asm/arch-sunxi/cpu.h
@@ -16,6 +16,7 @@
 
 #define SOCID_A64	0x1689
 #define SOCID_H3	0x1680
+#define SOCID_V3S	0x1681
 #define SOCID_H5	0x1718
 #define SOCID_R40	0x1701
 
diff --git a/arch/arm/mach-sunxi/dram_sunxi_dw.c b/arch/arm/mach-sunxi/dram_sunxi_dw.c
index a462538521..d0600011ff 100644
--- a/arch/arm/mach-sunxi/dram_sunxi_dw.c
+++ b/arch/arm/mach-sunxi/dram_sunxi_dw.c
@@ -63,6 +63,8 @@ enum {
 	MBUS_PORT_CSI           = 5,
 	MBUS_PORT_NAND          = 6,
 	MBUS_PORT_SS            = 7,
+	MBUS_PORT_DE_V3S        = 8,
+	MBUS_PORT_DE_CFD_V3S    = 9,
 	MBUS_PORT_TS            = 8,
 	MBUS_PORT_DI            = 9,
 	MBUS_PORT_DE            = 10,
@@ -134,6 +136,29 @@ static void mctl_set_master_priority_h3(void)
 	MBUS_CONF(DE_CFD,  true,    HIGH, 0, 1024,  288,   64);
 }
 
+static void mctl_set_master_priority_v3s(void)
+{
+	struct sunxi_mctl_com_reg * const mctl_com =
+			(struct sunxi_mctl_com_reg *)SUNXI_DRAM_COM_BASE;
+
+	/* enable bandwidth limit windows and set windows size 1us */
+	writel((1 << 16) | (400 << 0), &mctl_com->bwcr);
+
+	/* set cpu high priority */
+	writel(0x00000001, &mctl_com->mapr);
+
+	MBUS_CONF(       CPU,  true, HIGHEST, 0,  160,  100,   80);
+	MBUS_CONF(       GPU,  true,    HIGH, 0, 1792, 1536,    0);
+	MBUS_CONF(    UNUSED,  true, HIGHEST, 0,  256,  128,   80);
+	MBUS_CONF(       DMA,  true,    HIGH, 0,  256,  100,    0);
+	MBUS_CONF(        VE,  true,    HIGH, 0, 2048, 1600,    0);
+	MBUS_CONF(       CSI,  true, HIGHEST, 0,  384,  256,    0);
+	MBUS_CONF(      NAND,  true,    HIGH, 0,  100,   50,    0);
+	MBUS_CONF(        SS,  true,    HIGH, 0,  384,  256,    0);
+	MBUS_CONF(    DE_V3S, false,    HIGH, 0, 8192, 4096,    0);
+	MBUS_CONF(DE_CFD_V3S,  true,    HIGH, 0,  640,  256,    0);
+}
+
 static void mctl_set_master_priority_a64(void)
 {
 	struct sunxi_mctl_com_reg * const mctl_com =
@@ -231,6 +256,9 @@ static void mctl_set_master_priority(uint16_t socid)
 	case SOCID_H3:
 		mctl_set_master_priority_h3();
 		return;
+	case SOCID_V3S:
+		mctl_set_master_priority_v3s();
+		return;
 	case SOCID_A64:
 		mctl_set_master_priority_a64();
 		return;
@@ -334,6 +362,28 @@ static void mctl_h3_zq_calibration_quirk(struct dram_para *para)
 	}
 }
 
+static void mctl_v3s_zq_calibration_quirk(struct dram_para *para)
+{
+	struct sunxi_mctl_ctl_reg * const mctl_ctl =
+			(struct sunxi_mctl_ctl_reg *)SUNXI_DRAM_CTL0_BASE;
+
+	u32 reg_val;
+
+	clrsetbits_le32(&mctl_ctl->zqcr, 0xffffff,
+			CONFIG_DRAM_ZQ & 0xffffff);
+	mctl_phy_init(PIR_ZCAL);
+
+	reg_val = readl(&mctl_ctl->zqdr[0]);
+	reg_val &= (0x1f << 16) | (0x1f << 0);
+	reg_val |= reg_val << 8;
+	writel(reg_val, &mctl_ctl->zqdr[0]);
+
+	reg_val = readl(&mctl_ctl->zqdr[1]);
+	reg_val &= (0x1f << 16) | (0x1f << 0);
+	reg_val |= reg_val << 8;
+	writel(reg_val, &mctl_ctl->zqdr[1]);
+}
+
 static void mctl_set_cr(uint16_t socid, struct dram_para *para)
 {
 	struct sunxi_mctl_com_reg * const mctl_com =
@@ -391,7 +441,7 @@ static void mctl_sys_init(uint16_t socid, struct dram_para *para)
 				CCM_DRAMCLK_CFG_DIV(1) |
 				CCM_DRAMCLK_CFG_SRC_PLL11 |
 				CCM_DRAMCLK_CFG_UPD);
-	} else if (socid == SOCID_H3 || socid == SOCID_H5) {
+	} else if (socid == SOCID_H3 || socid == SOCID_H5 || socid == SOCID_V3S) {
 		clock_set_pll5(CONFIG_DRAM_CLK * 2 * 1000000, false);
 		clrsetbits_le32(&ccm->dram_clk_cfg,
 				CCM_DRAMCLK_CFG_DIV_MASK |
@@ -474,6 +524,13 @@ static int mctl_channel_init(uint16_t socid, struct dram_para *para)
 		/* dphy & aphy phase select 270 degree */
 		clrsetbits_le32(&mctl_ctl->pgcr[2], (0x3 << 10) | (0x3 << 8),
 				(0x1 << 10) | (0x2 << 8));
+	} else if (socid == SOCID_V3S) {
+		/* dx ddr_clk & hdr_clk dynamic mode */
+		clrbits_le32(&mctl_ctl->pgcr[0], (0x3 << 14) | (0x3 << 12));
+
+		/* dphy & aphy phase select 270 degree */
+		clrsetbits_le32(&mctl_ctl->pgcr[2], (0x3 << 10) | (0x3 << 8),
+				(0x1 << 10) | (0x1 << 8));
 	} else if (socid == SOCID_A64 || socid == SOCID_H5) {
 		/* dphy & aphy phase select ? */
 		clrsetbits_le32(&mctl_ctl->pgcr[2], (0x3 << 10) | (0x3 << 8),
@@ -506,7 +563,12 @@ static int mctl_channel_init(uint16_t socid, struct dram_para *para)
 	mctl_set_bit_delays(para);
 	udelay(50);
 
-	if (socid == SOCID_H3) {
+	if (socid == SOCID_V3S) {
+		mctl_v3s_zq_calibration_quirk(para);
+
+		mctl_phy_init(PIR_PLLINIT | PIR_DCAL | PIR_PHYRST |
+			      PIR_DRAMRST | PIR_DRAMINIT | PIR_QSGATE);
+	} else if (socid == SOCID_H3) {
 		mctl_h3_zq_calibration_quirk(para);
 
 		mctl_phy_init(PIR_PLLINIT | PIR_DCAL | PIR_PHYRST |
@@ -570,7 +632,7 @@ static int mctl_channel_init(uint16_t socid, struct dram_para *para)
 	udelay(10);
 
 	/* set PGCR3, CKE polarity */
-	if (socid == SOCID_H3)
+	if (socid == SOCID_H3 || socid == SOCID_V3S)
 		writel(0x00aa0060, &mctl_ctl->pgcr[3]);
 	else if (socid == SOCID_A64 || socid == SOCID_H5 || socid == SOCID_R40)
 		writel(0xc0aa0060, &mctl_ctl->pgcr[3]);
@@ -636,6 +698,22 @@ static void mctl_auto_detect_dram_size(uint16_t socid, struct dram_para *para)
 	   0,  0,  0,  0,  0,  0,  0,  0,			\
 	   0,  0,  0,  0,  0,  0,  0      }
 
+#define SUN8I_V3S_DX_READ_DELAYS					\
+	{{  8,  8,  8,  8,  8,  8,  8,  8,  8,  0,  0 },	\
+	 {  7,  7,  7,  7,  7,  7,  7,  7,  7,  0,  0 },	\
+	 {  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 },	\
+	 {  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 }}
+#define SUN8I_V3S_DX_WRITE_DELAYS				\
+	{{  0,  0,  0,  0,  0,  0,  0,  0,  0,  4,  4 },	\
+	 {  0,  0,  0,  0,  0,  0,  0,  0,  0,  2,  2 },	\
+	 {  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 },	\
+	 {  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0 }}
+#define SUN8I_V3S_AC_DELAYS					\
+	{  0,  0,  0,  0,  0,  0,  0,  0,			\
+	   0,  0,  0,  0,  0,  0,  0,  0,			\
+	   0,  0,  0,  0,  0,  0,  0,  0,			\
+	   0,  0,  0,  0,  0,  0,  0      }
+
 #define SUN8I_R40_DX_READ_DELAYS				\
 	{{ 14, 14, 14, 14, 14, 14, 14, 14, 14,  0,  0 },	\
 	 { 14, 14, 14, 14, 14, 14, 14, 14, 14,  0,  0 },	\
@@ -702,6 +780,10 @@ unsigned long sunxi_dram_init(void)
 		.dx_read_delays  = SUN8I_H3_DX_READ_DELAYS,
 		.dx_write_delays = SUN8I_H3_DX_WRITE_DELAYS,
 		.ac_delays	 = SUN8I_H3_AC_DELAYS,
+#elif defined(CONFIG_MACH_SUN8I_V3S)
+		.dx_read_delays  = SUN8I_V3S_DX_READ_DELAYS,
+		.dx_write_delays = SUN8I_V3S_DX_WRITE_DELAYS,
+		.ac_delays	 = SUN8I_V3S_AC_DELAYS,
 #elif defined(CONFIG_MACH_SUN8I_R40)
 		.dx_read_delays  = SUN8I_R40_DX_READ_DELAYS,
 		.dx_write_delays = SUN8I_R40_DX_WRITE_DELAYS,
@@ -728,8 +810,7 @@ unsigned long sunxi_dram_init(void)
 	/* Currently we cannot support R40 with dual rank memory */
 	para.dual_rank = 0;
 #elif defined(CONFIG_MACH_SUN8I_V3S)
-	/* TODO: set delays and mbus priority for V3s */
-	uint16_t socid = SOCID_H3;
+	uint16_t socid = SOCID_V3S;
 #elif defined(CONFIG_MACH_SUN50I)
 	uint16_t socid = SOCID_A64;
 #elif defined(CONFIG_MACH_SUN50I_H5)
diff --git a/board/sunxi/README.sunxi64 b/board/sunxi/README.sunxi64
index 258921af22..4803bc9ff2 100644
--- a/board/sunxi/README.sunxi64
+++ b/board/sunxi/README.sunxi64
@@ -14,8 +14,12 @@ Quick Start / Overview
 - Build the ARM Trusted Firmware binary (see "ARM Trusted Firmware (ATF)" below)
   $ cd /src/arm-trusted-firmware
   $ make PLAT=sun50i_a64 DEBUG=1 bl31
+- Build the SCP firmware binary (see "SCP firmware (Crust)" below)
+  $ cd /src/crust
+  $ make pine64_plus_defconfig && make -j5 scp
 - Build U-Boot (see "SPL/U-Boot" below)
   $ export BL31=/path/to/bl31.bin
+  $ export SCP=/src/crust/build/scp/scp.bin
   $ make pine64_plus_defconfig && make -j5
 - Transfer to an uSD card (see "microSD card" below)
   $ dd if=u-boot-sunxi-with-spl.bin of=/dev/sdx bs=8k seek=1
@@ -24,13 +28,17 @@ Quick Start / Overview
 Building the firmware
 =====================
 
-The Allwinner A64/H5 firmware consists of three parts: U-Boot's SPL, an
-ARM Trusted Firmware (ATF) build and the U-Boot proper.
-The SPL will load both ATF and U-Boot proper along with the right device
-tree blob (.dtb) and will pass execution to ATF (in EL3), which in turn will
-drop into the U-Boot proper (in EL2).
-As the ATF binary will become part of the U-Boot image file, you will need
-to build it first.
+The Allwinner A64/H5/H6 firmware consists of several parts: U-Boot's SPL,
+ARM Trusted Firmware (ATF), optional System Control Processor (SCP) firmware
+(e.g. Crust), and the U-Boot proper.
+
+The SPL will load all of the other firmware binaries into RAM, along with the
+right device tree blob (.dtb), and will pass execution to ATF (in EL3). If SCP
+firmware was loaded, ATF will power on the SCP and wait for it to boot.
+ATF will then drop into U-Boot proper (in EL2).
+
+As the ATF binary and SCP firmware will become part of the U-Boot image file,
+you will need to build them first.
 
  ARM Trusted Firmware (ATF)
 ----------------------------
@@ -53,6 +61,31 @@ As sometimes the ATF build process is a bit picky about the toolchain used,
 or if you can't be bothered with building ATF, there are known working
 binaries in the firmware repository[3], purely for convenience reasons.
 
+ SCP firmware (Crust)
+----------------------
+SCP firmware is responsible for implementing system suspend/resume, and (on
+boards without a PMIC) soft poweroff/on. ATF contains fallback code for CPU
+power control, so SCP firmware is optional if you don't need either of these
+features. It runs on the AR100, with is an or1k CPU, not ARM, so it needs a
+different cross toolchain.
+
+There is one SCP firmware implementation currently available, Crust:
+$ git clone https://github.com/crust-firmware/crust
+$ cd crust
+$ export CROSS_COMPILE=or1k-linux-musl-
+$ make pine64_plus_defconfig
+$ make scp
+
+The same configuration generally works on any board with the same SoC (A64, H5,
+or H6), so if there is no config for your board, use one for a similar board.
+
+Like for ATF, U-Boot finds the SCP firmware binary via an environment variable:
+$ export SCP=/src/crust/build/scp/scp.bin
+
+If you do not want to use SCP firmware, you can silence the warning from binman
+by pointing it to an empty file:
+$ export SCP=/dev/null
+
  SPL/U-Boot
 ------------
 Both U-Boot proper and the SPL are using the 64-bit mode. As the boot ROM
diff --git a/common/spl/Kconfig b/common/spl/Kconfig
index af47f5ce1c..d8086bd9e8 100644
--- a/common/spl/Kconfig
+++ b/common/spl/Kconfig
@@ -465,9 +465,7 @@ config SPL_FIT_IMAGE_TINY
 	  Enable this to reduce the size of the FIT image loading code
 	  in SPL, if space for the SPL binary is very tight.
 
-	  This removes the detection of image types (which forces the
-	  first image to be treated as having a U-Boot style calling
-	  convention) and skips the recording of each loaded payload
+	  This skips the recording of each loaded payload
 	  (i.e. loadable) into the FDT (modifying the loaded FDT to
 	  ensure this information is available to the next image
 	  invoked).
diff --git a/common/spl/spl_fit.c b/common/spl/spl_fit.c
index a90d821c82..fd6086a65c 100644
--- a/common/spl/spl_fit.c
+++ b/common/spl/spl_fit.c
@@ -466,7 +466,22 @@ static int spl_fit_record_loadable(const void *fit, int images, int index,
 static int spl_fit_image_get_os(const void *fit, int noffset, uint8_t *os)
 {
 #if CONFIG_IS_ENABLED(FIT_IMAGE_TINY) && !defined(CONFIG_SPL_OS_BOOT)
-	return -ENOTSUPP;
+	const char *name = fdt_getprop(fit, noffset, FIT_OS_PROP, NULL);
+
+	if (!name)
+		return -ENOENT;
+
+	/*
+	 * We don't care what the type of the image actually is,
+	 * only whether or not it is U-Boot. This saves some
+	 * space by omitting the large table of OS types.
+	 */
+	if (!strcmp(name, "u-boot"))
+		*os = IH_OS_U_BOOT;
+	else
+		*os = IH_OS_INVALID;
+
+	return 0;
 #else
 	return fit_image_get_os(fit, noffset, os);
 #endif
diff --git a/configs/A20-OLinuXino-Lime2-eMMC_defconfig b/configs/A20-OLinuXino-Lime2-eMMC_defconfig
index b1a38d7a4d..f9f8f14151 100644
--- a/configs/A20-OLinuXino-Lime2-eMMC_defconfig
+++ b/configs/A20-OLinuXino-Lime2-eMMC_defconfig
@@ -19,6 +19,8 @@ CONFIG_CMD_USB_MASS_STORAGE=y
 CONFIG_SCSI_AHCI=y
 CONFIG_DFU_RAM=y
 CONFIG_FASTBOOT_CMD_OEM_FORMAT=y
+CONFIG_PHY_MICREL=y
+CONFIG_PHY_MICREL_KSZ90X1=y
 CONFIG_PHY_REALTEK=y
 CONFIG_ETH_DESIGNWARE=y
 CONFIG_RGMII=y
diff --git a/configs/pine_h64_defconfig b/configs/pine_h64_defconfig
index 328849d724..07ad31e3a7 100644
--- a/configs/pine_h64_defconfig
+++ b/configs/pine_h64_defconfig
@@ -11,5 +11,6 @@ CONFIG_SPL_SPI_SUNXI=y
 CONFIG_DEFAULT_DEVICE_TREE="sun50i-h6-pine-h64"
 # CONFIG_SYS_MALLOC_CLEAR_ON_INIT is not set
 CONFIG_SUN8I_EMAC=y
+CONFIG_MACPWR="PC16"
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_OHCI_HCD=y
diff --git a/configs/teres_i_defconfig b/configs/teres_i_defconfig
index 1eba20e5f5..ee07f86f64 100644
--- a/configs/teres_i_defconfig
+++ b/configs/teres_i_defconfig
@@ -7,6 +7,7 @@ CONFIG_DRAM_ZQ=3881949
 CONFIG_MMC_SUNXI_SLOT_EXTRA=2
 CONFIG_USB1_VBUS_PIN="PL7"
 CONFIG_I2C0_ENABLE=y
+CONFIG_PREBOOT="setenv usb_pgood_delay 2000; usb start"
 CONFIG_DEFAULT_DEVICE_TREE="sun50i-a64-teres-i"
 CONFIG_DM_REGULATOR=y
 CONFIG_DM_REGULATOR_FIXED=y
diff --git a/doc/git-mailrc b/doc/git-mailrc
index 31595a71c9..bbca3a9a37 100644
--- a/doc/git-mailrc
+++ b/doc/git-mailrc
@@ -36,7 +36,7 @@ alias marex          Marek Vasut <marex@denx.de>
 alias mariosix       Mario Six <mario.six@gdsys.cc>
 alias masahiro       Masahiro Yamada <yamada.masahiro@socionext.com>
 alias mateusz        Mateusz Kulikowski <mateusz.kulikowski@gmail.com>
-alias maxime         Maxime Ripard <maxime.ripard@free-electrons.com>
+alias maxime         Maxime Ripard <mripard@kernel.org>
 alias mbrugger       Matthias Brugger <mbrugger@suse.com>
 alias monstr         Michal Simek <monstr@monstr.eu>
 alias prom           Minkyu Kang <mk7.kang@samsung.com>
diff --git a/drivers/net/sun8i_emac.c b/drivers/net/sun8i_emac.c
index 1dae81c7bf..4524604126 100644
--- a/drivers/net/sun8i_emac.c
+++ b/drivers/net/sun8i_emac.c
@@ -29,6 +29,7 @@
 #include <net.h>
 #include <reset.h>
 #include <dt-bindings/pinctrl/sun4i-a10.h>
+#include <wait_bit.h>
 #if CONFIG_IS_ENABLED(DM_GPIO)
 #include <asm-generic/gpio.h>
 #endif
@@ -40,6 +41,11 @@
 #define MDIO_CMD_MII_PHY_REG_ADDR_SHIFT	4
 #define MDIO_CMD_MII_PHY_ADDR_MASK	0x0001f000
 #define MDIO_CMD_MII_PHY_ADDR_SHIFT	12
+#define MDIO_CMD_MII_CLK_CSR_DIV_16	0x0
+#define MDIO_CMD_MII_CLK_CSR_DIV_32	0x1
+#define MDIO_CMD_MII_CLK_CSR_DIV_64	0x2
+#define MDIO_CMD_MII_CLK_CSR_DIV_128	0x3
+#define MDIO_CMD_MII_CLK_CSR_SHIFT	20
 
 #define CONFIG_TX_DESCR_NUM	32
 #define CONFIG_RX_DESCR_NUM	32
@@ -84,15 +90,32 @@
 
 /* H3/A64 EMAC Register's offset */
 #define EMAC_CTL0		0x00
+#define EMAC_CTL0_FULL_DUPLEX		BIT(0)
+#define EMAC_CTL0_SPEED_MASK		GENMASK(3, 2)
+#define EMAC_CTL0_SPEED_10		(0x2 << 2)
+#define EMAC_CTL0_SPEED_100		(0x3 << 2)
+#define EMAC_CTL0_SPEED_1000		(0x0 << 2)
 #define EMAC_CTL1		0x04
+#define EMAC_CTL1_SOFT_RST		BIT(0)
+#define EMAC_CTL1_BURST_LEN_SHIFT	24
 #define EMAC_INT_STA		0x08
 #define EMAC_INT_EN		0x0c
 #define EMAC_TX_CTL0		0x10
+#define	EMAC_TX_CTL0_TX_EN		BIT(31)
 #define EMAC_TX_CTL1		0x14
+#define	EMAC_TX_CTL1_TX_MD		BIT(1)
+#define	EMAC_TX_CTL1_TX_DMA_EN		BIT(30)
+#define	EMAC_TX_CTL1_TX_DMA_START	BIT(31)
 #define EMAC_TX_FLOW_CTL	0x1c
 #define EMAC_TX_DMA_DESC	0x20
 #define EMAC_RX_CTL0		0x24
+#define	EMAC_RX_CTL0_RX_EN		BIT(31)
 #define EMAC_RX_CTL1		0x28
+#define	EMAC_RX_CTL1_RX_MD		BIT(1)
+#define	EMAC_RX_CTL1_RX_RUNT_FRM	BIT(2)
+#define	EMAC_RX_CTL1_RX_ERR_FRM		BIT(3)
+#define	EMAC_RX_CTL1_RX_DMA_EN		BIT(30)
+#define	EMAC_RX_CTL1_RX_DMA_START	BIT(31)
 #define EMAC_RX_DMA_DESC	0x34
 #define EMAC_MII_CMD		0x48
 #define EMAC_MII_DATA		0x4c
@@ -104,6 +127,13 @@
 #define EMAC_RX_DMA_STA		0xc0
 #define EMAC_RX_CUR_DESC	0xc4
 
+#define EMAC_DESC_OWN_DMA	BIT(31)
+#define EMAC_DESC_LAST_DESC	BIT(30)
+#define EMAC_DESC_FIRST_DESC	BIT(29)
+#define EMAC_DESC_CHAIN_SECOND	BIT(24)
+
+#define EMAC_DESC_RX_ERROR_MASK	0x400068db
+
 DECLARE_GLOBAL_DATA_PTR;
 
 enum emac_variant {
@@ -116,7 +146,7 @@ enum emac_variant {
 
 struct emac_dma_desc {
 	u32 status;
-	u32 st;
+	u32 ctl_size;
 	u32 buf_addr;
 	u32 next;
 } __aligned(ARCH_DMA_MINALIGN);
@@ -166,32 +196,31 @@ static int sun8i_mdio_read(struct mii_dev *bus, int addr, int devad, int reg)
 {
 	struct udevice *dev = bus->priv;
 	struct emac_eth_dev *priv = dev_get_priv(dev);
-	ulong start;
-	u32 miiaddr = 0;
-	int timeout = CONFIG_MDIO_TIMEOUT;
+	u32 mii_cmd;
+	int ret;
 
-	miiaddr &= ~MDIO_CMD_MII_WRITE;
-	miiaddr &= ~MDIO_CMD_MII_PHY_REG_ADDR_MASK;
-	miiaddr |= (reg << MDIO_CMD_MII_PHY_REG_ADDR_SHIFT) &
+	mii_cmd = (reg << MDIO_CMD_MII_PHY_REG_ADDR_SHIFT) &
 		MDIO_CMD_MII_PHY_REG_ADDR_MASK;
-
-	miiaddr &= ~MDIO_CMD_MII_PHY_ADDR_MASK;
-
-	miiaddr |= (addr << MDIO_CMD_MII_PHY_ADDR_SHIFT) &
+	mii_cmd |= (addr << MDIO_CMD_MII_PHY_ADDR_SHIFT) &
 		MDIO_CMD_MII_PHY_ADDR_MASK;
 
-	miiaddr |= MDIO_CMD_MII_BUSY;
+	/*
+	 * The EMAC clock is either 200 or 300 MHz, so we need a divider
+	 * of 128 to get the MDIO frequency below the required 2.5 MHz.
+	 */
+	mii_cmd |= MDIO_CMD_MII_CLK_CSR_DIV_128 << MDIO_CMD_MII_CLK_CSR_SHIFT;
 
-	writel(miiaddr, priv->mac_reg + EMAC_MII_CMD);
+	mii_cmd |= MDIO_CMD_MII_BUSY;
 
-	start = get_timer(0);
-	while (get_timer(start) < timeout) {
-		if (!(readl(priv->mac_reg + EMAC_MII_CMD) & MDIO_CMD_MII_BUSY))
-			return readl(priv->mac_reg + EMAC_MII_DATA);
-		udelay(10);
-	};
+	writel(mii_cmd, priv->mac_reg + EMAC_MII_CMD);
 
-	return -1;
+	ret = wait_for_bit_le32(priv->mac_reg + EMAC_MII_CMD,
+				MDIO_CMD_MII_BUSY, false,
+				CONFIG_MDIO_TIMEOUT, true);
+	if (ret < 0)
+		return ret;
+
+	return readl(priv->mac_reg + EMAC_MII_DATA);
 }
 
 static int sun8i_mdio_write(struct mii_dev *bus, int addr, int devad, int reg,
@@ -199,39 +228,35 @@ static int sun8i_mdio_write(struct mii_dev *bus, int addr, int devad, int reg,
 {
 	struct udevice *dev = bus->priv;
 	struct emac_eth_dev *priv = dev_get_priv(dev);
-	ulong start;
-	u32 miiaddr = 0;
-	int ret = -1, timeout = CONFIG_MDIO_TIMEOUT;
+	u32 mii_cmd;
 
-	miiaddr &= ~MDIO_CMD_MII_PHY_REG_ADDR_MASK;
-	miiaddr |= (reg << MDIO_CMD_MII_PHY_REG_ADDR_SHIFT) &
+	mii_cmd = (reg << MDIO_CMD_MII_PHY_REG_ADDR_SHIFT) &
 		MDIO_CMD_MII_PHY_REG_ADDR_MASK;
-
-	miiaddr &= ~MDIO_CMD_MII_PHY_ADDR_MASK;
-	miiaddr |= (addr << MDIO_CMD_MII_PHY_ADDR_SHIFT) &
+	mii_cmd |= (addr << MDIO_CMD_MII_PHY_ADDR_SHIFT) &
 		MDIO_CMD_MII_PHY_ADDR_MASK;
 
-	miiaddr |= MDIO_CMD_MII_WRITE;
-	miiaddr |= MDIO_CMD_MII_BUSY;
+	/*
+	 * The EMAC clock is either 200 or 300 MHz, so we need a divider
+	 * of 128 to get the MDIO frequency below the required 2.5 MHz.
+	 */
+	mii_cmd |= MDIO_CMD_MII_CLK_CSR_DIV_128 << MDIO_CMD_MII_CLK_CSR_SHIFT;
+
+	mii_cmd |= MDIO_CMD_MII_WRITE;
+	mii_cmd |= MDIO_CMD_MII_BUSY;
 
 	writel(val, priv->mac_reg + EMAC_MII_DATA);
-	writel(miiaddr, priv->mac_reg + EMAC_MII_CMD);
+	writel(mii_cmd, priv->mac_reg + EMAC_MII_CMD);
 
-	start = get_timer(0);
-	while (get_timer(start) < timeout) {
-		if (!(readl(priv->mac_reg + EMAC_MII_CMD) &
-					MDIO_CMD_MII_BUSY)) {
-			ret = 0;
-			break;
-		}
-		udelay(10);
-	};
-
-	return ret;
+	return wait_for_bit_le32(priv->mac_reg + EMAC_MII_CMD,
+				 MDIO_CMD_MII_BUSY, false,
+				 CONFIG_MDIO_TIMEOUT, true);
 }
 
-static int _sun8i_write_hwaddr(struct emac_eth_dev *priv, u8 *mac_id)
+static int sun8i_eth_write_hwaddr(struct udevice *dev)
 {
+	struct emac_eth_dev *priv = dev_get_priv(dev);
+	struct eth_pdata *pdata = dev_get_platdata(dev);
+	uchar *mac_id = pdata->enetaddr;
 	u32 macid_lo, macid_hi;
 
 	macid_lo = mac_id[0] + (mac_id[1] << 8) + (mac_id[2] << 16) +
@@ -252,21 +277,21 @@ static void sun8i_adjust_link(struct emac_eth_dev *priv,
 	v = readl(priv->mac_reg + EMAC_CTL0);
 
 	if (phydev->duplex)
-		v |= BIT(0);
+		v |= EMAC_CTL0_FULL_DUPLEX;
 	else
-		v &= ~BIT(0);
+		v &= ~EMAC_CTL0_FULL_DUPLEX;
 
-	v &= ~0x0C;
+	v &= ~EMAC_CTL0_SPEED_MASK;
 
 	switch (phydev->speed) {
 	case 1000:
+		v |= EMAC_CTL0_SPEED_1000;
 		break;
 	case 100:
-		v |= BIT(2);
-		v |= BIT(3);
+		v |= EMAC_CTL0_SPEED_100;
 		break;
 	case 10:
-		v |= BIT(3);
+		v |= EMAC_CTL0_SPEED_10;
 		break;
 	}
 	writel(v, priv->mac_reg + EMAC_CTL0);
@@ -372,24 +397,36 @@ static int sun8i_phy_init(struct emac_eth_dev *priv, void *dev)
 	return 0;
 }
 
+#define cache_clean_descriptor(desc)					\
+	flush_dcache_range((uintptr_t)(desc), 				\
+			   (uintptr_t)(desc) + sizeof(struct emac_dma_desc))
+
+#define cache_inv_descriptor(desc)					\
+	invalidate_dcache_range((uintptr_t)(desc),			\
+			       (uintptr_t)(desc) + sizeof(struct emac_dma_desc))
+
 static void rx_descs_init(struct emac_eth_dev *priv)
 {
 	struct emac_dma_desc *desc_table_p = &priv->rx_chain[0];
 	char *rxbuffs = &priv->rxbuffer[0];
 	struct emac_dma_desc *desc_p;
-	u32 idx;
+	int i;
 
-	/* flush Rx buffers */
-	flush_dcache_range((uintptr_t)rxbuffs, (ulong)rxbuffs +
-			RX_TOTAL_BUFSIZE);
+	/*
+	 * Make sure we don't have dirty cache lines around, which could
+	 * be cleaned to DRAM *after* the MAC has already written data to it.
+	 */
+	invalidate_dcache_range((uintptr_t)desc_table_p,
+			      (uintptr_t)desc_table_p + sizeof(priv->rx_chain));
+	invalidate_dcache_range((uintptr_t)rxbuffs,
+				(uintptr_t)rxbuffs + sizeof(priv->rxbuffer));
 
-	for (idx = 0; idx < CONFIG_RX_DESCR_NUM; idx++) {
-		desc_p = &desc_table_p[idx];
-		desc_p->buf_addr = (uintptr_t)&rxbuffs[idx * CONFIG_ETH_BUFSIZE]
-			;
-		desc_p->next = (uintptr_t)&desc_table_p[idx + 1];
-		desc_p->st |= CONFIG_ETH_RXSIZE;
-		desc_p->status = BIT(31);
+	for (i = 0; i < CONFIG_RX_DESCR_NUM; i++) {
+		desc_p = &desc_table_p[i];
+		desc_p->buf_addr = (uintptr_t)&rxbuffs[i * CONFIG_ETH_BUFSIZE];
+		desc_p->next = (uintptr_t)&desc_table_p[i + 1];
+		desc_p->ctl_size = CONFIG_ETH_RXSIZE;
+		desc_p->status = EMAC_DESC_OWN_DMA;
 	}
 
 	/* Correcting the last pointer of the chain */
@@ -408,87 +445,74 @@ static void tx_descs_init(struct emac_eth_dev *priv)
 	struct emac_dma_desc *desc_table_p = &priv->tx_chain[0];
 	char *txbuffs = &priv->txbuffer[0];
 	struct emac_dma_desc *desc_p;
-	u32 idx;
+	int i;
 
-	for (idx = 0; idx < CONFIG_TX_DESCR_NUM; idx++) {
-		desc_p = &desc_table_p[idx];
-		desc_p->buf_addr = (uintptr_t)&txbuffs[idx * CONFIG_ETH_BUFSIZE]
-			;
-		desc_p->next = (uintptr_t)&desc_table_p[idx + 1];
-		desc_p->status = (1 << 31);
-		desc_p->st = 0;
+	for (i = 0; i < CONFIG_TX_DESCR_NUM; i++) {
+		desc_p = &desc_table_p[i];
+		desc_p->buf_addr = (uintptr_t)&txbuffs[i * CONFIG_ETH_BUFSIZE];
+		desc_p->next = (uintptr_t)&desc_table_p[i + 1];
+		desc_p->ctl_size = 0;
+		desc_p->status = 0;
 	}
 
 	/* Correcting the last pointer of the chain */
 	desc_p->next =  (uintptr_t)&desc_table_p[0];
 
-	/* Flush all Tx buffer descriptors */
-	flush_dcache_range((uintptr_t)priv->tx_chain,
-			   (uintptr_t)priv->tx_chain +
-			sizeof(priv->tx_chain));
+	/* Flush the first TX buffer descriptor we will tell the MAC about. */
+	cache_clean_descriptor(desc_table_p);
 
 	writel((uintptr_t)&desc_table_p[0], priv->mac_reg + EMAC_TX_DMA_DESC);
 	priv->tx_currdescnum = 0;
 }
 
-static int _sun8i_emac_eth_init(struct emac_eth_dev *priv, u8 *enetaddr)
+static int sun8i_emac_eth_start(struct udevice *dev)
 {
-	u32 reg, v;
-	int timeout = 100;
+	struct emac_eth_dev *priv = dev_get_priv(dev);
+	int ret;
 
-	reg = readl((priv->mac_reg + EMAC_CTL1));
-
-	if (!(reg & 0x1)) {
-		/* Soft reset MAC */
-		setbits_le32((priv->mac_reg + EMAC_CTL1), 0x1);
-		do {
-			reg = readl(priv->mac_reg + EMAC_CTL1);
-		} while ((reg & 0x01) != 0 &&  (--timeout));
-		if (!timeout) {
-			printf("%s: Timeout\n", __func__);
-			return -1;
-		}
+	/* Soft reset MAC */
+	writel(EMAC_CTL1_SOFT_RST, priv->mac_reg + EMAC_CTL1);
+	ret = wait_for_bit_le32(priv->mac_reg + EMAC_CTL1,
+				EMAC_CTL1_SOFT_RST, false, 10, true);
+	if (ret) {
+		printf("%s: Timeout\n", __func__);
+		return ret;
 	}
 
 	/* Rewrite mac address after reset */
-	_sun8i_write_hwaddr(priv, enetaddr);
+	sun8i_eth_write_hwaddr(dev);
 
-	v = readl(priv->mac_reg + EMAC_TX_CTL1);
-	/* TX_MD Transmission starts after a full frame located in TX DMA FIFO*/
-	v |= BIT(1);
-	writel(v, priv->mac_reg + EMAC_TX_CTL1);
+	/* transmission starts after the full frame arrived in TX DMA FIFO */
+	setbits_le32(priv->mac_reg + EMAC_TX_CTL1, EMAC_TX_CTL1_TX_MD);
 
-	v = readl(priv->mac_reg + EMAC_RX_CTL1);
-	/* RX_MD RX DMA reads data from RX DMA FIFO to host memory after a
+	/*
+	 * RX DMA reads data from RX DMA FIFO to host memory after a
 	 * complete frame has been written to RX DMA FIFO
 	 */
-	v |= BIT(1);
-	writel(v, priv->mac_reg + EMAC_RX_CTL1);
+	setbits_le32(priv->mac_reg + EMAC_RX_CTL1, EMAC_RX_CTL1_RX_MD);
 
-	/* DMA */
-	writel(8 << 24, priv->mac_reg + EMAC_CTL1);
+	/* DMA burst length */
+	writel(8 << EMAC_CTL1_BURST_LEN_SHIFT, priv->mac_reg + EMAC_CTL1);
 
 	/* Initialize rx/tx descriptors */
 	rx_descs_init(priv);
 	tx_descs_init(priv);
 
 	/* PHY Start Up */
-	phy_startup(priv->phydev);
+	ret = phy_startup(priv->phydev);
+	if (ret)
+		return ret;
 
 	sun8i_adjust_link(priv, priv->phydev);
 
-	/* Start RX DMA */
-	v = readl(priv->mac_reg + EMAC_RX_CTL1);
-	v |= BIT(30);
-	writel(v, priv->mac_reg + EMAC_RX_CTL1);
-	/* Start TX DMA */
-	v = readl(priv->mac_reg + EMAC_TX_CTL1);
-	v |= BIT(30);
-	writel(v, priv->mac_reg + EMAC_TX_CTL1);
+	/* Start RX/TX DMA */
+	setbits_le32(priv->mac_reg + EMAC_RX_CTL1, EMAC_RX_CTL1_RX_DMA_EN |
+		     EMAC_RX_CTL1_RX_ERR_FRM | EMAC_RX_CTL1_RX_RUNT_FRM);
+	setbits_le32(priv->mac_reg + EMAC_TX_CTL1, EMAC_TX_CTL1_TX_DMA_EN);
 
 	/* Enable RX/TX */
-	setbits_le32(priv->mac_reg + EMAC_RX_CTL0, BIT(31));
-	setbits_le32(priv->mac_reg + EMAC_TX_CTL0, BIT(31));
+	setbits_le32(priv->mac_reg + EMAC_RX_CTL0, EMAC_RX_CTL0_RX_EN);
+	setbits_le32(priv->mac_reg + EMAC_TX_CTL0, EMAC_TX_CTL0_TX_EN);
 
 	return 0;
 }
@@ -558,88 +582,71 @@ static int parse_phy_pins(struct udevice *dev)
 	return 0;
 }
 
-static int _sun8i_eth_recv(struct emac_eth_dev *priv, uchar **packetp)
+static int sun8i_emac_eth_recv(struct udevice *dev, int flags, uchar **packetp)
 {
+	struct emac_eth_dev *priv = dev_get_priv(dev);
 	u32 status, desc_num = priv->rx_currdescnum;
 	struct emac_dma_desc *desc_p = &priv->rx_chain[desc_num];
-	int length = -EAGAIN;
-	int good_packet = 1;
-	uintptr_t desc_start = (uintptr_t)desc_p;
-	uintptr_t desc_end = desc_start +
-		roundup(sizeof(*desc_p), ARCH_DMA_MINALIGN);
-
-	ulong data_start = (uintptr_t)desc_p->buf_addr;
-	ulong data_end;
+	uintptr_t data_start = (uintptr_t)desc_p->buf_addr;
+	int length;
 
 	/* Invalidate entire buffer descriptor */
-	invalidate_dcache_range(desc_start, desc_end);
+	cache_inv_descriptor(desc_p);
 
 	status = desc_p->status;
 
 	/* Check for DMA own bit */
-	if (!(status & BIT(31))) {
-		length = (desc_p->status >> 16) & 0x3FFF;
+	if (status & EMAC_DESC_OWN_DMA)
+		return -EAGAIN;
 
-		if (length < 0x40) {
-			good_packet = 0;
-			debug("RX: Bad Packet (runt)\n");
-		}
+	length = (status >> 16) & 0x3fff;
 
-		data_end = data_start + length;
-		/* Invalidate received data */
-		invalidate_dcache_range(rounddown(data_start,
-						  ARCH_DMA_MINALIGN),
-					roundup(data_end,
-						ARCH_DMA_MINALIGN));
-		if (good_packet) {
-			if (length > CONFIG_ETH_RXSIZE) {
-				printf("Received packet is too big (len=%d)\n",
-				       length);
-				return -EMSGSIZE;
-			}
-			*packetp = (uchar *)(ulong)desc_p->buf_addr;
-			return length;
-		}
+	/* make sure we read from DRAM, not our cache */
+	invalidate_dcache_range(data_start,
+				data_start + roundup(length, ARCH_DMA_MINALIGN));
+
+	if (status & EMAC_DESC_RX_ERROR_MASK) {
+		debug("RX: packet error: 0x%x\n",
+		      status & EMAC_DESC_RX_ERROR_MASK);
+		return 0;
 	}
+	if (length < 0x40) {
+		debug("RX: Bad Packet (runt)\n");
+		return 0;
+	}
+
+	if (length > CONFIG_ETH_RXSIZE) {
+		debug("RX: Too large packet (%d bytes)\n", length);
+		return 0;
+	}
+
+	*packetp = (uchar *)(ulong)desc_p->buf_addr;
 
 	return length;
 }
 
-static int _sun8i_emac_eth_send(struct emac_eth_dev *priv, void *packet,
-				int len)
+static int sun8i_emac_eth_send(struct udevice *dev, void *packet, int length)
 {
-	u32 v, desc_num = priv->tx_currdescnum;
+	struct emac_eth_dev *priv = dev_get_priv(dev);
+	u32 desc_num = priv->tx_currdescnum;
 	struct emac_dma_desc *desc_p = &priv->tx_chain[desc_num];
-	uintptr_t desc_start = (uintptr_t)desc_p;
-	uintptr_t desc_end = desc_start +
-		roundup(sizeof(*desc_p), ARCH_DMA_MINALIGN);
-
 	uintptr_t data_start = (uintptr_t)desc_p->buf_addr;
 	uintptr_t data_end = data_start +
-		roundup(len, ARCH_DMA_MINALIGN);
+		roundup(length, ARCH_DMA_MINALIGN);
 
-	/* Invalidate entire buffer descriptor */
-	invalidate_dcache_range(desc_start, desc_end);
+	desc_p->ctl_size = length | EMAC_DESC_CHAIN_SECOND;
 
-	desc_p->st = len;
-	/* Mandatory undocumented bit */
-	desc_p->st |= BIT(24);
-
-	memcpy((void *)data_start, packet, len);
+	memcpy((void *)data_start, packet, length);
 
 	/* Flush data to be sent */
 	flush_dcache_range(data_start, data_end);
 
-	/* frame end */
-	desc_p->st |= BIT(30);
-	desc_p->st |= BIT(31);
+	/* frame begin and end */
+	desc_p->ctl_size |= EMAC_DESC_LAST_DESC | EMAC_DESC_FIRST_DESC;
+	desc_p->status = EMAC_DESC_OWN_DMA;
 
-	/*frame begin */
-	desc_p->st |= BIT(29);
-	desc_p->status = BIT(31);
-
-	/*Descriptors st and status field has changed, so FLUSH it */
-	flush_dcache_range(desc_start, desc_end);
+	/* make sure the MAC reads the actual data from DRAM */
+	cache_clean_descriptor(desc_p);
 
 	/* Move to next Descriptor and wrap around */
 	if (++desc_num >= CONFIG_TX_DESCR_NUM)
@@ -647,22 +654,16 @@ static int _sun8i_emac_eth_send(struct emac_eth_dev *priv, void *packet,
 	priv->tx_currdescnum = desc_num;
 
 	/* Start the DMA */
-	v = readl(priv->mac_reg + EMAC_TX_CTL1);
-	v |= BIT(31);/* mandatory */
-	v |= BIT(30);/* mandatory */
-	writel(v, priv->mac_reg + EMAC_TX_CTL1);
+	setbits_le32(priv->mac_reg + EMAC_TX_CTL1, EMAC_TX_CTL1_TX_DMA_START);
+
+	/*
+	 * Since we copied the data above, we return here without waiting
+	 * for the packet to be actually send out.
+	 */
 
 	return 0;
 }
 
-static int sun8i_eth_write_hwaddr(struct udevice *dev)
-{
-	struct eth_pdata *pdata = dev_get_platdata(dev);
-	struct emac_eth_dev *priv = dev_get_priv(dev);
-
-	return _sun8i_write_hwaddr(priv, pdata->enetaddr);
-}
-
 static int sun8i_emac_board_setup(struct udevice *dev,
 				  struct emac_eth_dev *priv)
 {
@@ -760,40 +761,18 @@ static int sun8i_mdio_init(const char *name, struct udevice *priv)
 	return  mdio_register(bus);
 }
 
-static int sun8i_emac_eth_start(struct udevice *dev)
-{
-	struct eth_pdata *pdata = dev_get_platdata(dev);
-
-	return _sun8i_emac_eth_init(dev->priv, pdata->enetaddr);
-}
-
-static int sun8i_emac_eth_send(struct udevice *dev, void *packet, int length)
+static int sun8i_eth_free_pkt(struct udevice *dev, uchar *packet,
+			      int length)
 {
 	struct emac_eth_dev *priv = dev_get_priv(dev);
-
-	return _sun8i_emac_eth_send(priv, packet, length);
-}
-
-static int sun8i_emac_eth_recv(struct udevice *dev, int flags, uchar **packetp)
-{
-	struct emac_eth_dev *priv = dev_get_priv(dev);
-
-	return _sun8i_eth_recv(priv, packetp);
-}
-
-static int _sun8i_free_pkt(struct emac_eth_dev *priv)
-{
 	u32 desc_num = priv->rx_currdescnum;
 	struct emac_dma_desc *desc_p = &priv->rx_chain[desc_num];
-	uintptr_t desc_start = (uintptr_t)desc_p;
-	uintptr_t desc_end = desc_start +
-		roundup(sizeof(u32), ARCH_DMA_MINALIGN);
 
-	/* Make the current descriptor valid again */
-	desc_p->status |= BIT(31);
+	/* give the current descriptor back to the MAC */
+	desc_p->status |= EMAC_DESC_OWN_DMA;
 
 	/* Flush Status field of descriptor */
-	flush_dcache_range(desc_start, desc_end);
+	cache_clean_descriptor(desc_p);
 
 	/* Move to next desc and wrap-around condition. */
 	if (++desc_num >= CONFIG_RX_DESCR_NUM)
@@ -803,24 +782,17 @@ static int _sun8i_free_pkt(struct emac_eth_dev *priv)
 	return 0;
 }
 
-static int sun8i_eth_free_pkt(struct udevice *dev, uchar *packet,
-			      int length)
-{
-	struct emac_eth_dev *priv = dev_get_priv(dev);
-
-	return _sun8i_free_pkt(priv);
-}
-
 static void sun8i_emac_eth_stop(struct udevice *dev)
 {
 	struct emac_eth_dev *priv = dev_get_priv(dev);
 
 	/* Stop Rx/Tx transmitter */
-	clrbits_le32(priv->mac_reg + EMAC_RX_CTL0, BIT(31));
-	clrbits_le32(priv->mac_reg + EMAC_TX_CTL0, BIT(31));
+	clrbits_le32(priv->mac_reg + EMAC_RX_CTL0, EMAC_RX_CTL0_RX_EN);
+	clrbits_le32(priv->mac_reg + EMAC_TX_CTL0, EMAC_TX_CTL0_TX_EN);
 
-	/* Stop TX DMA */
-	clrbits_le32(priv->mac_reg + EMAC_TX_CTL1, BIT(30));
+	/* Stop RX/TX DMA */
+	clrbits_le32(priv->mac_reg + EMAC_TX_CTL1, EMAC_TX_CTL1_TX_DMA_EN);
+	clrbits_le32(priv->mac_reg + EMAC_RX_CTL1, EMAC_RX_CTL1_RX_DMA_EN);
 
 	phy_shutdown(priv->phydev);
 }
@@ -855,47 +827,30 @@ static const struct eth_ops sun8i_emac_eth_ops = {
 	.stop                   = sun8i_emac_eth_stop,
 };
 
-static int sun8i_get_ephy_nodes(struct udevice *dev, struct emac_eth_dev *priv)
+static int sun8i_handle_internal_phy(struct udevice *dev, struct emac_eth_dev *priv)
 {
-	int emac_node, ephy_node, ret, ephy_handle;
+	struct ofnode_phandle_args phandle;
+	int ret;
 
-	emac_node = fdt_path_offset(gd->fdt_blob,
-				    "/soc/ethernet@1c30000");
-	if (emac_node < 0) {
-		debug("failed to get emac node\n");
-		return emac_node;
-	}
-	ephy_handle = fdtdec_lookup_phandle(gd->fdt_blob,
-					    emac_node, "phy-handle");
+	ret = ofnode_parse_phandle_with_args(dev_ofnode(dev), "phy-handle",
+					     NULL, 0, 0, &phandle);
+	if (ret)
+		return ret;
 
-	/* look for mdio-mux node for internal PHY node */
-	ephy_node = fdt_path_offset(gd->fdt_blob,
-				    "/soc/ethernet@1c30000/mdio-mux/mdio@1/ethernet-phy@1");
-	if (ephy_node < 0) {
-		debug("failed to get mdio-mux with internal PHY\n");
-		return ephy_node;
-	}
-
-	/* This is not the phy we are looking for */
-	if (ephy_node != ephy_handle)
+	/* If the PHY node is not a child of the internal MDIO bus, we are
+	 * using some external PHY.
+	 */
+	if (!ofnode_device_is_compatible(ofnode_get_parent(phandle.node),
+					 "allwinner,sun8i-h3-mdio-internal"))
 		return 0;
 
-	ret = fdt_node_check_compatible(gd->fdt_blob, ephy_node,
-					"allwinner,sun8i-h3-mdio-internal");
-	if (ret < 0) {
-		debug("failed to find mdio-internal node\n");
-		return ret;
-	}
-
-	ret = clk_get_by_index_nodev(offset_to_ofnode(ephy_node), 0,
-				     &priv->ephy_clk);
+	ret = clk_get_by_index_nodev(phandle.node, 0, &priv->ephy_clk);
 	if (ret) {
 		dev_err(dev, "failed to get EPHY TX clock\n");
 		return ret;
 	}
 
-	ret = reset_get_by_index_nodev(offset_to_ofnode(ephy_node), 0,
-				       &priv->ephy_rst);
+	ret = reset_get_by_index_nodev(phandle.node, 0, &priv->ephy_rst);
 	if (ret) {
 		dev_err(dev, "failed to get EPHY TX reset\n");
 		return ret;
@@ -987,7 +942,7 @@ static int sun8i_emac_eth_ofdata_to_platdata(struct udevice *dev)
 	}
 
 	if (priv->variant == H3_EMAC) {
-		ret = sun8i_get_ephy_nodes(dev, priv);
+		ret = sun8i_handle_internal_phy(dev, priv);
 		if (ret)
 			return ret;
 	}
diff --git a/tools/binman/README.entries b/tools/binman/README.entries
index c1d436563e..bdb4fd6ee5 100644
--- a/tools/binman/README.entries
+++ b/tools/binman/README.entries
@@ -385,8 +385,8 @@ You can create config nodes in a similar way:
         default = "@config-DEFAULT-SEQ";
         @config-SEQ {
             description = "NAME";
-            firmware = "uboot";
-            loadables = "atf";
+            firmware = "atf";
+            loadables = "uboot";
             fdt = "fdt-SEQ";
         };
     };
diff --git a/tools/binman/etype/fit.py b/tools/binman/etype/fit.py
index de4745c552..1a7cbd7cec 100644
--- a/tools/binman/etype/fit.py
+++ b/tools/binman/etype/fit.py
@@ -73,8 +73,8 @@ class Entry_fit(Entry):
             default = "@config-DEFAULT-SEQ";
             @config-SEQ {
                 description = "NAME";
-                firmware = "uboot";
-                loadables = "atf";
+                firmware = "atf";
+                loadables = "uboot";
                 fdt = "fdt-SEQ";
             };
         };
@@ -205,10 +205,10 @@ class Entry_fit(Entry):
                                         b'SEQ', tools.ToBytes(str(seq + 1)))
                                     fsw.property(pname, val)
 
-                                    # Add data for 'fdt' nodes (but not 'config')
-                                    if depth == 1 and in_images:
-                                        fsw.property('data',
-                                                     tools.ReadFile(fname))
+                                # Add data for 'fdt' nodes (but not 'config')
+                                if depth == 1 and in_images:
+                                    fsw.property('data',
+                                                 tools.ReadFile(fname))
                     else:
                         if self._fdts is None:
                             if self._fit_list_prop:
diff --git a/tools/binman/etype/scp.py b/tools/binman/etype/scp.py
new file mode 100644
index 0000000000..93f8787d2d
--- /dev/null
+++ b/tools/binman/etype/scp.py
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright 2020 Samuel Holland <samuel@sholland.org>
+#
+# Entry-type module for System Control Processor (SCP) firmware blob
+#
+
+from binman.etype.blob_named_by_arg import Entry_blob_named_by_arg
+
+class Entry_scp(Entry_blob_named_by_arg):
+    """Entry containing a System Control Processor (SCP) firmware blob
+
+    Properties / Entry arguments:
+        - scp-path: Filename of file to read into the entry, typically scp.bin
+
+    This entry holds firmware for an external platform-specific coprocessor.
+    """
+    def __init__(self, section, etype, node):
+        super().__init__(section, etype, node, 'scp')
+        self.external = True
diff --git a/tools/binman/ftest.py b/tools/binman/ftest.py
index b771b9d5df..75f6ca3a89 100644
--- a/tools/binman/ftest.py
+++ b/tools/binman/ftest.py
@@ -75,6 +75,7 @@ FSP_M_DATA            = b'fsp_m'
 FSP_S_DATA            = b'fsp_s'
 FSP_T_DATA            = b'fsp_t'
 ATF_BL31_DATA         = b'bl31'
+SCP_DATA              = b'scp'
 TEST_FDT1_DATA        = b'fdt1'
 TEST_FDT2_DATA        = b'test-fdt2'
 ENV_DATA              = b'var1=1\nvar2="2"'
@@ -175,6 +176,7 @@ class TestFunctional(unittest.TestCase):
 
         TestFunctional._MakeInputFile('compress', COMPRESS_DATA)
         TestFunctional._MakeInputFile('bl31.bin', ATF_BL31_DATA)
+        TestFunctional._MakeInputFile('scp.bin', SCP_DATA)
 
         # Add a few .dtb files for testing
         TestFunctional._MakeInputFile('%s/test-fdt1.dtb' % TEST_FDT_SUBDIR,
@@ -3578,6 +3580,11 @@ class TestFunctional(unittest.TestCase):
         data = self._DoReadFile('169_atf_bl31.dts')
         self.assertEqual(ATF_BL31_DATA, data[:len(ATF_BL31_DATA)])
 
+    def testPackScp(self):
+        """Test that an image with an SCP binary can be created"""
+        data = self._DoReadFile('172_scp.dts')
+        self.assertEqual(SCP_DATA, data[:len(SCP_DATA)])
+
     def testFitFdt(self):
         """Test an image with an FIT with multiple FDT images"""
         def _CheckFdt(seq, expected_data):
diff --git a/tools/binman/missing-blob-help b/tools/binman/missing-blob-help
index 7cf1c34610..f7bc80ea83 100644
--- a/tools/binman/missing-blob-help
+++ b/tools/binman/missing-blob-help
@@ -13,3 +13,7 @@ Firmware and build with BL31=/path/to/bl31.bin
 atf-bl31-sunxi:
 Please read the section on ARM Trusted Firmware (ATF) in
 board/sunxi/README.sunxi64
+
+scp-sunxi:
+SCP firmware is required for system suspend, but is otherwise optional.
+Please read the section on SCP firmware in board/sunxi/README.sunxi64
diff --git a/tools/binman/test/172_scp.dts b/tools/binman/test/172_scp.dts
new file mode 100644
index 0000000000..354e4ef17d
--- /dev/null
+++ b/tools/binman/test/172_scp.dts
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/dts-v1/;
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	binman {
+		size = <16>;
+
+		scp {
+			filename = "scp.bin";
+		};
+	};
+};