Merge branch 'next' of git://git.denx.de/u-boot-sh

This is part 1 of big network cleanup / DM conversion.
The dc2114x/rtl8139/pcnet/tulip PCI adapter drivers received checkpatch
cleanups in preparation for DM conversion. The smc911x is converted to
DM completely. The dwc_eth_qos cache fixes are applied.
diff --git a/.readthedocs.yml b/.readthedocs.yml
index f3fb5ed..44949ea 100644
--- a/.readthedocs.yml
+++ b/.readthedocs.yml
@@ -7,7 +7,7 @@
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
-  configuration: docs/conf.py
+  configuration: doc/conf.py
 
 # Optionally build your docs in additional formats such as PDF and ePub
 formats: []
diff --git a/Kconfig b/Kconfig
index 9a5e600..15f1a75 100644
--- a/Kconfig
+++ b/Kconfig
@@ -209,6 +209,20 @@
 	  When disabling this, please check if malloc calls, maybe
 	  should be replaced by calloc - if one expects zeroed memory.
 
+config SYS_MALLOC_DEFAULT_TO_INIT
+	bool "Default malloc to init while reserving the memory for it"
+	default n
+	help
+	  It may happen that one needs to move the dynamic allocation
+	  from one to another memory range, eg. when moving the malloc
+	  from the limited static to a potentially large dynamic (DDR)
+	  memory.
+
+	  If so then on top of setting the updated memory aside one
+	  needs to bring the malloc init.
+
+	  If such a scenario is sought choose yes.
+
 config TOOLS_DEBUG
 	bool "Enable debug information for tools"
 	help
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 8e67e1c..b494bca 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -340,6 +340,34 @@
 	default 64 if SYS_CACHE_SHIFT_6
 	default 32 if SYS_CACHE_SHIFT_5
 
+choice
+	prompt "Select the ARM data write cache policy"
+	default SYS_ARM_CACHE_WRITETHROUGH if TARGET_BCMCYGNUS || \
+					      TARGET_BCMNSP || CPU_PXA || RZA1
+	default SYS_ARM_CACHE_WRITEBACK
+
+config SYS_ARM_CACHE_WRITEBACK
+	bool "Write-back (WB)"
+	help
+	  A write updates the cache only and marks the cache line as dirty.
+	  External memory is updated only when the line is evicted or explicitly
+	  cleaned.
+
+config SYS_ARM_CACHE_WRITETHROUGH
+	bool "Write-through (WT)"
+	help
+	  A write updates both the cache and the external memory system.
+	  This does not mark the cache line as dirty.
+
+config SYS_ARM_CACHE_WRITEALLOC
+	bool "Write allocation (WA)"
+	help
+	  A cache line is allocated on a write miss. This means that executing a
+	  store instruction on the processor might cause a burst read to occur.
+	  There is a linefill to obtain the data for the cache line, before the
+	  write is performed.
+endchoice
+
 config ARCH_CPU_INIT
 	bool "Enable ARCH_CPU_INIT"
 	help
@@ -881,7 +909,7 @@
 	select CLK
 	select CLK_OWL
 	select OF_CONTROL
-	select CONFIG_SYS_RELOC_GD_ENV_ADDR
+	select SYS_RELOC_GD_ENV_ADDR
 	imply CMD_DM
 
 config ARCH_QEMU
diff --git a/arch/arm/include/asm/iproc-common/configs.h b/arch/arm/include/asm/iproc-common/configs.h
index 96c4f54..4733c07 100644
--- a/arch/arm/include/asm/iproc-common/configs.h
+++ b/arch/arm/include/asm/iproc-common/configs.h
@@ -10,7 +10,6 @@
 
 /* Architecture, CPU, chip, etc */
 #define CONFIG_IPROC
-#define CONFIG_SYS_ARM_CACHE_WRITETHROUGH
 
 /* Memory Info */
 #define CONFIG_SYS_SDRAM_BASE		0x61000000
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 81ccead..a3147fd 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -485,6 +485,14 @@
 };
 #endif
 
+#if defined(CONFIG_SYS_ARM_CACHE_WRITETHROUGH)
+#define DCACHE_DEFAULT_OPTION	DCACHE_WRITETHROUGH
+#elif defined(CONFIG_SYS_ARM_CACHE_WRITEALLOC)
+#define DCACHE_DEFAULT_OPTION	DCACHE_WRITEALLOC
+#elif defined(CONFIG_SYS_ARM_CACHE_WRITEBACK)
+#define DCACHE_DEFAULT_OPTION	DCACHE_WRITEBACK
+#endif
+
 /* Size of an MMU section */
 enum {
 #ifdef CONFIG_ARMV7_LPAE
diff --git a/arch/arm/lib/cache-cp15.c b/arch/arm/lib/cache-cp15.c
index f8d2096..f803d6f 100644
--- a/arch/arm/lib/cache-cp15.c
+++ b/arch/arm/lib/cache-cp15.c
@@ -61,8 +61,11 @@
 	unsigned long startpt, stoppt;
 	unsigned long upto, end;
 
-	end = ALIGN(start + size, MMU_SECTION_SIZE) >> MMU_SECTION_SHIFT;
+	/* div by 2 before start + size to avoid phys_addr_t overflow */
+	end = ALIGN((start / 2) + (size / 2), MMU_SECTION_SIZE / 2)
+	      >> (MMU_SECTION_SHIFT - 1);
 	start = start >> MMU_SECTION_SHIFT;
+
 #ifdef CONFIG_ARMV7_LPAE
 	debug("%s: start=%pa, size=%zu, option=%llx\n", __func__, &start, size,
 	      option);
@@ -91,19 +94,16 @@
 	bd_t *bd = gd->bd;
 	int	i;
 
+	/* bd->bi_dram is available only after relocation */
+	if ((gd->flags & GD_FLG_RELOC) == 0)
+		return;
+
 	debug("%s: bank: %d\n", __func__, bank);
 	for (i = bd->bi_dram[bank].start >> MMU_SECTION_SHIFT;
 	     i < (bd->bi_dram[bank].start >> MMU_SECTION_SHIFT) +
 		 (bd->bi_dram[bank].size >> MMU_SECTION_SHIFT);
-	     i++) {
-#if defined(CONFIG_SYS_ARM_CACHE_WRITETHROUGH)
-		set_section_dcache(i, DCACHE_WRITETHROUGH);
-#elif defined(CONFIG_SYS_ARM_CACHE_WRITEALLOC)
-		set_section_dcache(i, DCACHE_WRITEALLOC);
-#else
-		set_section_dcache(i, DCACHE_WRITEBACK);
-#endif
-	}
+	     i++)
+		set_section_dcache(i, DCACHE_DEFAULT_OPTION);
 }
 
 /* to activate the MMU we need to set up virtual memory: use 1M areas */
diff --git a/arch/arm/lib/interrupts.c b/arch/arm/lib/interrupts.c
index 6dbf03b..36299d6 100644
--- a/arch/arm/lib/interrupts.c
+++ b/arch/arm/lib/interrupts.c
@@ -34,6 +34,8 @@
 	 */
 	IRQ_STACK_START_IN = gd->irq_sp + 8;
 
+	enable_interrupts();
+
 	return 0;
 }
 
diff --git a/arch/arm/lib/interrupts_64.c b/arch/arm/lib/interrupts_64.c
index dffdf57..a2df7cf 100644
--- a/arch/arm/lib/interrupts_64.c
+++ b/arch/arm/lib/interrupts_64.c
@@ -13,6 +13,8 @@
 
 int interrupt_init(void)
 {
+	enable_interrupts();
+
 	return 0;
 }
 
diff --git a/arch/arm/lib/interrupts_m.c b/arch/arm/lib/interrupts_m.c
index 1f6fdf2..2ae1c5b 100644
--- a/arch/arm/lib/interrupts_m.c
+++ b/arch/arm/lib/interrupts_m.c
@@ -31,6 +31,8 @@
 
 int interrupt_init(void)
 {
+	enable_interrupts();
+
 	return 0;
 }
 
diff --git a/arch/riscv/dts/hifive-unleashed-a00-u-boot.dtsi b/arch/riscv/dts/hifive-unleashed-a00-u-boot.dtsi
new file mode 100644
index 0000000..2aebfab
--- /dev/null
+++ b/arch/riscv/dts/hifive-unleashed-a00-u-boot.dtsi
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2019 Jagan Teki <jagan@amarulasolutions.com>
+ */
+
+/ {
+	aliases {
+		spi0 = &qspi0;
+		spi2 = &qspi2;
+	};
+};
diff --git a/board/sifive/fu540/Kconfig b/board/sifive/fu540/Kconfig
index 5ca2147..75661f3 100644
--- a/board/sifive/fu540/Kconfig
+++ b/board/sifive/fu540/Kconfig
@@ -26,6 +26,7 @@
 	imply CMD_FS_GENERIC
 	imply CMD_NET
 	imply CMD_PING
+	imply CMD_SF
 	imply CLK_SIFIVE
 	imply CLK_SIFIVE_FU540_PRCI
 	imply DOS_PARTITION
@@ -40,6 +41,8 @@
 	imply SIFIVE_SERIAL
 	imply SPI
 	imply SPI_SIFIVE
+	imply SPI_FLASH
+	imply SPI_FLASH_ISSI
 	imply MMC
 	imply MMC_SPI
 	imply MMC_BROKEN_CD
diff --git a/cmd/bedbug.c b/cmd/bedbug.c
index 9fee528..d3e3121 100644
--- a/cmd/bedbug.c
+++ b/cmd/bedbug.c
@@ -44,10 +44,10 @@
  * settings.
  * ====================================================================== */
 
-void bedbug_init (void)
+int bedbug_init(void)
 {
 	/* -------------------------------------------------- */
-	return;
+	return 0;
 }				/* bedbug_init */
 
 
diff --git a/cmd/gpt.c b/cmd/gpt.c
index b94f005..b8d11c1 100644
--- a/cmd/gpt.c
+++ b/cmd/gpt.c
@@ -772,11 +772,9 @@
  out:
 	del_gpt_info();
 #ifdef CONFIG_RANDOM_UUID
-	if (str_disk_guid)
-		free(str_disk_guid);
+	free(str_disk_guid);
 #endif
-	if (new_partitions)
-		free(new_partitions);
+	free(new_partitions);
 	free(partitions_list);
 	return ret;
 }
diff --git a/common/board_r.c b/common/board_r.c
index 0bbeaa7..d9015cd 100644
--- a/common/board_r.c
+++ b/common/board_r.c
@@ -518,15 +518,6 @@
 }
 #endif
 
-/* enable exceptions */
-#ifdef CONFIG_ARM
-static int initr_enable_interrupts(void)
-{
-	enable_interrupts();
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_CMD_NET
 static int initr_ethaddr(void)
 {
@@ -646,15 +637,6 @@
 }
 #endif
 
-#ifdef CONFIG_CMD_BEDBUG
-static int initr_bedbug(void)
-{
-	bedbug_init();
-
-	return 0;
-}
-#endif
-
 static int run_main_loop(void)
 {
 #ifdef CONFIG_SANDBOX
@@ -813,9 +795,6 @@
 	initr_kgdb,
 #endif
 	interrupt_init,
-#ifdef CONFIG_ARM
-	initr_enable_interrupts,
-#endif
 #if defined(CONFIG_MICROBLAZE) || defined(CONFIG_M68K)
 	timer_init,		/* initialize timer */
 #endif
@@ -860,7 +839,7 @@
 #endif
 #ifdef CONFIG_CMD_BEDBUG
 	INIT_FUNC_WATCHDOG_RESET
-	initr_bedbug,
+	bedbug_init,
 #endif
 #if defined(CONFIG_PRAM)
 	initr_mem,
diff --git a/common/cli_hush.c b/common/cli_hush.c
index cf1e273..a62af07 100644
--- a/common/cli_hush.c
+++ b/common/cli_hush.c
@@ -1849,8 +1849,7 @@
 				continue;
 			} else {
 				/* insert new value from list for variable */
-				if (pi->progs->argv[0])
-					free(pi->progs->argv[0]);
+				free(pi->progs->argv[0]);
 				pi->progs->argv[0] = *list++;
 #ifndef __U_BOOT__
 				pi->progs->glob_result.gl_pathv[0] =
diff --git a/common/dlmalloc.c b/common/dlmalloc.c
index db5ab55..e8f07f1 100644
--- a/common/dlmalloc.c
+++ b/common/dlmalloc.c
@@ -280,6 +280,7 @@
 	    |             Unused space (may be 0 bytes long)                .
 	    .                                                               .
 	    .                                                               |
+
 nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
     `foot:' |             Size of chunk, in bytes                           |
 	    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -574,6 +575,10 @@
 static inline void malloc_bin_reloc(void) {}
 #endif
 
+#ifdef CONFIG_SYS_MALLOC_DEFAULT_TO_INIT
+static void malloc_init(void);
+#endif
+
 ulong mem_malloc_start = 0;
 ulong mem_malloc_end = 0;
 ulong mem_malloc_brk = 0;
@@ -604,6 +609,10 @@
 	mem_malloc_end = start + size;
 	mem_malloc_brk = start;
 
+#ifdef CONFIG_SYS_MALLOC_DEFAULT_TO_INIT
+	malloc_init();
+#endif
+
 	debug("using memory %#lx-%#lx for malloc()\n", mem_malloc_start,
 	      mem_malloc_end);
 #ifdef CONFIG_SYS_MALLOC_CLEAR_ON_INIT
@@ -708,7 +717,36 @@
 static unsigned long max_mmapped_mem = 0;
 #endif
 
+#ifdef CONFIG_SYS_MALLOC_DEFAULT_TO_INIT
+static void malloc_init(void)
+{
+	int i, j;
+
+	debug("bins (av_ array) are at %p\n", (void *)av_);
+
+	av_[0] = NULL; av_[1] = NULL;
+	for (i = 2, j = 2; i < NAV * 2 + 2; i += 2, j++) {
+		av_[i] = bin_at(j - 2);
+		av_[i + 1] = bin_at(j - 2);
 
+		/* Just print the first few bins so that
+		 * we can see there are alright.
+		 */
+		if (i < 10)
+			debug("av_[%d]=%lx av_[%d]=%lx\n",
+			      i, (ulong)av_[i],
+			      i + 1, (ulong)av_[i + 1]);
+	}
+
+	/* Init the static bookkeeping as well */
+	sbrk_base = (char *)(-1);
+	max_sbrked_mem = 0;
+	max_total_mem = 0;
+#ifdef DEBUG
+	memset((void *)&current_mallinfo, 0, sizeof(struct mallinfo));
+#endif
+}
+#endif
 
 /*
   Debugging support
@@ -1051,9 +1089,6 @@
 
 #endif /* HAVE_MMAP */
 
-
-
-
 /*
   Extend the top-most chunk by obtaining memory from system.
   Main interface to sbrk (but see also malloc_trim).
diff --git a/common/image-fit-sig.c b/common/image-fit-sig.c
index 3e73578..a3a0c61 100644
--- a/common/image-fit-sig.c
+++ b/common/image-fit-sig.c
@@ -249,7 +249,7 @@
 				int required_keynode, int conf_noffset,
 				char **err_msgp)
 {
-	char * const exc_prop[] = {"data"};
+	char * const exc_prop[] = {"data", "data-size", "data-position"};
 	const char *prop, *end, *name;
 	struct image_sign_info info;
 	const uint32_t *strings;
diff --git a/configs/mt7623n_bpir2_defconfig b/configs/mt7623n_bpir2_defconfig
index 07ddade..fe28f37 100644
--- a/configs/mt7623n_bpir2_defconfig
+++ b/configs/mt7623n_bpir2_defconfig
@@ -7,6 +7,7 @@
 CONFIG_ENV_OFFSET=0x100000
 CONFIG_TARGET_MT7623=y
 CONFIG_NR_DRAM_BANKS=1
+CONFIG_DISTRO_DEFAULTS=y
 CONFIG_FIT=y
 CONFIG_FIT_VERBOSE=y
 CONFIG_BOOTDELAY=3
@@ -56,4 +57,4 @@
 CONFIG_MTK_TIMER=y
 CONFIG_WDT_MTK=y
 CONFIG_LZMA=y
-# CONFIG_EFI_LOADER is not set
+CONFIG_EFI_LOADER=y
diff --git a/doc/develop/crash_dumps.rst b/doc/develop/crash_dumps.rst
new file mode 100644
index 0000000..1869637
--- /dev/null
+++ b/doc/develop/crash_dumps.rst
@@ -0,0 +1,122 @@
+.. SPDX-License-Identifier: GPL-2.0+
+.. Copyright (c) 2020 Heinrich Schuchardt
+
+Analyzing crash dumps
+=====================
+
+When the CPU detects an instruction that it cannot execute it raises an
+interrupt. U-Boot than writes a crash dump. This chapter describes how such
+dump can be analyzed.
+
+Creating a crash dump voluntarily
+---------------------------------
+
+For describing the analysis of a crash dump we need an example. U-Boot comes
+with a command 'exception' that comes in handy here. The command is enabled
+by::
+
+    CONFIG_CMD_EXCEPTION=y
+
+The example output below was recorded when running qemu\_arm64\_defconfig on
+QEMU::
+
+    => exception undefined
+    "Synchronous Abort" handler, esr 0x02000000
+    elr: 00000000000101fc lr : 00000000000214ec (reloc)
+    elr: 000000007ff291fc lr : 000000007ff3a4ec
+    x0 : 000000007ffbd7f8 x1 : 0000000000000000
+    x2 : 0000000000000001 x3 : 000000007eedce18
+    x4 : 000000007ff291fc x5 : 000000007eedce50
+    x6 : 0000000000000064 x7 : 000000007eedce10
+    x8 : 0000000000000000 x9 : 0000000000000004
+    x10: 6db6db6db6db6db7 x11: 000000000000000d
+    x12: 0000000000000006 x13: 000000000001869f
+    x14: 000000007edd7dc0 x15: 0000000000000002
+    x16: 000000007ff291fc x17: 0000000000000000
+    x18: 000000007eed8dc0 x19: 0000000000000000
+    x20: 000000007ffbd7f8 x21: 0000000000000000
+    x22: 000000007eedce10 x23: 0000000000000002
+    x24: 000000007ffd4c80 x25: 0000000000000000
+    x26: 0000000000000000 x27: 0000000000000000
+    x28: 000000007eedce70 x29: 000000007edd7b40
+
+    Code: b00003c0 912ad000 940029d6 17ffff52 (e7f7defb)
+    Resetting CPU ...
+
+    resetting ...
+
+The first line provides us with the type of interrupt that occurred.
+(On ARMv8 a synchronous abort is an exception where the return address stored
+in the ESR register indicates the instruction that caused the exception.)
+
+The second line provides the contents of the elr and the lr register after
+subtracting the relocation offset. - U-Boot relocates itself after being
+loaded. - The relocation offset can also be displayed using the bdinfo command.
+
+After the contents of the registers we get a line indicating the machine
+code of the instructions preceding the crash and in parentheses the instruction
+leading to the dump.
+
+Analyzing the code location
+---------------------------
+
+We can convert the instructions in the line starting with 'Code:' into mnemonics
+using the objdump command. To make things easier scripts/decodecode is
+supplied::
+
+    $echo 'Code: b00003c0 912ad000 940029d6 17ffff52 (e7f7defb)' | \
+      CROSS_COMPILE=aarch64-linux-gnu- ARCH=arm64 scripts/decodecode
+    Code: b00003c0 912ad000 940029d6 17ffff52 (e7f7defb)
+    All code
+    ========
+       0:   b00003c0     adrp   x0, 0x79000
+       4:   912ad000     add    x0, x0, #0xab4
+       8:   940029d6     bl     0xa760
+       c:   17ffff52     b      0xfffffffffffffd54
+      10:*  e7f7defb     .inst  0xe7f7defb ; undefined <-- trapping instruction
+
+    Code starting with the faulting instruction
+    ===========================================
+       0:   e7f7defb     .inst  0xe7f7defb ; undefined
+
+Now lets use the locations provided by the elr and lr registers after
+subtracting the relocation offset to find out where in the code the crash
+occurred and from where it was invoked.
+
+File u-boot.map contains the memory layout of the U-Boot binary. Here we find
+these lines::
+
+   .text.do_undefined
+                  0x00000000000101fc        0xc cmd/built-in.o
+   .text.exception_complete
+                  0x0000000000010208       0x90 cmd/built-in.o
+   ...
+   .text.cmd_process
+                  0x00000000000213b8      0x164 common/built-in.o
+                  0x00000000000213b8                cmd_process
+   .text.cmd_process_error
+                  0x000000000002151c       0x40 common/built-in.o
+                  0x000000000002151c                cmd_process_error
+
+So the error occurred at the start of function do\_undefined() and this
+function was invoked from somewhere inside function cmd\_process().
+
+If we want to dive deeper, we can disassemble the U-Boot binary::
+
+    $ aarch64-linux-gnu-objdump -S -D u-boot | less
+
+    00000000000101fc <do_undefined>:
+    {
+            /*
+             * 0xe7f...f.   is undefined in ARM mode
+             * 0xde..       is undefined in Thumb mode
+            */
+            asm volatile (".word 0xe7f7defb\n");
+       101fc:       e7f7defb        .inst   0xe7f7defb ; undefined
+            return CMD_RET_FAILURE;
+    }
+    10200:       52800020        mov     w0, #0x1        // #1
+    10204:       d65f03c0        ret
+
+This example is based on the ARMv8 architecture but the same procedures can be
+used on other architectures as well.
diff --git a/doc/develop/index.rst b/doc/develop/index.rst
new file mode 100644
index 0000000..072db63
--- /dev/null
+++ b/doc/develop/index.rst
@@ -0,0 +1,10 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Develop U-Boot
+==============
+
+
+.. toctree::
+   :maxdepth: 2
+
+   crash_dumps
diff --git a/doc/index.rst b/doc/index.rst
index cd98be6..fd9f10f 100644
--- a/doc/index.rst
+++ b/doc/index.rst
@@ -26,6 +26,17 @@
 
    build/index
 
+Developer-oriented documentation
+--------------------------------
+
+The following manuals are written for *developers* of the U-Boot - those who
+want to contribute to U-Boot.
+
+.. toctree::
+   :maxdepth: 2
+
+   develop/index
+
 Unified Extensible Firmware (UEFI)
 ----------------------------------
 
diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
index dd6baca..6c65b18 100644
--- a/drivers/mtd/nand/spi/Makefile
+++ b/drivers/mtd/nand/spi/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
-spinand-objs := core.o gigadevice.o macronix.o micron.o winbond.o
+spinand-objs := core.o gigadevice.o macronix.o micron.o toshiba.o winbond.o
 obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index cd624ec..397dfa4 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -835,6 +835,7 @@
 	&gigadevice_spinand_manufacturer,
 	&macronix_spinand_manufacturer,
 	&micron_spinand_manufacturer,
+	&toshiba_spinand_manufacturer,
 	&winbond_spinand_manufacturer,
 };
 
diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c
new file mode 100644
index 0000000..77c2539
--- /dev/null
+++ b/drivers/mtd/nand/spi/toshiba.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 exceet electronics GmbH
+ * Copyright (c) 2018 Kontron Electronics GmbH
+ *
+ * Author: Frieder Schrempf <frieder.schrempf@kontron.de>
+ */
+
+#ifndef __UBOOT__
+#include <malloc.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#endif
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_TOSHIBA		0x98
+#define TOSH_STATUS_ECC_HAS_BITFLIPS_T	(3 << 4)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int tc58cxgxsx_ooblayout_ecc(struct mtd_info *mtd, int section,
+				     struct mtd_oob_region *region)
+{
+	if (section > 0)
+		return -ERANGE;
+
+	region->offset = mtd->oobsize / 2;
+	region->length = mtd->oobsize / 2;
+
+	return 0;
+}
+
+static int tc58cxgxsx_ooblayout_free(struct mtd_info *mtd, int section,
+				      struct mtd_oob_region *region)
+{
+	if (section > 0)
+		return -ERANGE;
+
+	/* 2 bytes reserved for BBM */
+	region->offset = 2;
+	region->length = (mtd->oobsize / 2) - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops tc58cxgxsx_ooblayout = {
+	.ecc = tc58cxgxsx_ooblayout_ecc,
+	.rfree = tc58cxgxsx_ooblayout_free,
+};
+
+static int tc58cxgxsx_ecc_get_status(struct spinand_device *spinand,
+				      u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	u8 mbf = 0;
+	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, &mbf);
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+	case TOSH_STATUS_ECC_HAS_BITFLIPS_T:
+		/*
+		 * Let's try to retrieve the real maximum number of bitflips
+		 * in order to avoid forcing the wear-leveling layer to move
+		 * data around if it's not necessary.
+		 */
+		if (spi_mem_exec_op(spinand->slave, &op))
+			return nand->eccreq.strength;
+
+		mbf >>= 4;
+
+		if (WARN_ON(mbf > nand->eccreq.strength || !mbf))
+			return nand->eccreq.strength;
+
+		return mbf;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info toshiba_spinand_table[] = {
+	/* 3.3V 1Gb */
+	SPINAND_INFO("TC58CVG0S3", 0xC2,
+		     NAND_MEMORG(1, 2048, 128, 64, 1024, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
+	/* 3.3V 2Gb */
+	SPINAND_INFO("TC58CVG1S3", 0xCB,
+		     NAND_MEMORG(1, 2048, 128, 64, 2048, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
+	/* 3.3V 4Gb */
+	SPINAND_INFO("TC58CVG2S0", 0xCD,
+		     NAND_MEMORG(1, 4096, 256, 64, 2048, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
+	/* 3.3V 4Gb */
+	SPINAND_INFO("TC58CVG2S0", 0xED,
+		     NAND_MEMORG(1, 4096, 256, 64, 2048, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
+	/* 1.8V 1Gb */
+	SPINAND_INFO("TC58CYG0S3", 0xB2,
+		     NAND_MEMORG(1, 2048, 128, 64, 1024, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
+	/* 1.8V 2Gb */
+	SPINAND_INFO("TC58CYG1S3", 0xBB,
+		     NAND_MEMORG(1, 2048, 128, 64, 2048, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
+	/* 1.8V 4Gb */
+	SPINAND_INFO("TC58CYG2S0", 0xBD,
+		     NAND_MEMORG(1, 4096, 256, 64, 2048, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
+};
+
+static int toshiba_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Toshiba SPI NAND read ID needs a dummy byte,
+	 * so the first byte in id is garbage.
+	 */
+	if (id[1] != SPINAND_MFR_TOSHIBA)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, toshiba_spinand_table,
+				     ARRAY_SIZE(toshiba_spinand_table),
+				     id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops toshiba_spinand_manuf_ops = {
+	.detect = toshiba_spinand_detect,
+};
+
+const struct spinand_manufacturer toshiba_spinand_manufacturer = {
+	.id = SPINAND_MFR_TOSHIBA,
+	.name = "Toshiba",
+	.ops = &toshiba_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/spi/spi-nor-core.c b/drivers/mtd/spi/spi-nor-core.c
index 7b6ad49..e840c60 100644
--- a/drivers/mtd/spi/spi-nor-core.c
+++ b/drivers/mtd/spi/spi-nor-core.c
@@ -325,6 +325,7 @@
 	case SNOR_MFR_MICRON:
 		/* Some Micron need WREN command; all will accept it */
 		need_wren = true;
+	case SNOR_MFR_ISSI:
 	case SNOR_MFR_MACRONIX:
 	case SNOR_MFR_WINBOND:
 		if (need_wren)
@@ -1246,11 +1247,8 @@
 		 * If page_size is a power of two, the offset can be quickly
 		 * calculated with an AND operation. On the other cases we
 		 * need to do a modulus operation (more expensive).
-		 * Power of two numbers have only one bit set and we can use
-		 * the instruction hweight32 to detect if we need to do a
-		 * modulus (do_div()) or not.
 		 */
-		if (hweight32(nor->page_size) == 1) {
+		if (is_power_of_2(nor->page_size)) {
 			page_offset = addr & (nor->page_size - 1);
 		} else {
 			u64 aux = addr;
diff --git a/drivers/mtd/spi/spi-nor-ids.c b/drivers/mtd/spi/spi-nor-ids.c
index abdf560..e5e7102 100644
--- a/drivers/mtd/spi/spi-nor-ids.c
+++ b/drivers/mtd/spi/spi-nor-ids.c
@@ -135,7 +135,8 @@
 	{ INFO("is25wp128",  0x9d7018, 0, 64 * 1024, 256,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ INFO("is25wp256",  0x9d7019, 0, 64 * 1024, 512,
-			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_4B_OPCODES) },
 #endif
 #ifdef CONFIG_SPI_FLASH_MACRONIX	/* MACRONIX */
 	/* Macronix */
@@ -183,8 +184,8 @@
 	{ INFO("n25q00",      0x20ba21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
 	{ INFO("n25q00a",     0x20bb21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
 	{ INFO("mt25qu02g",   0x20bb22, 0, 64 * 1024, 4096, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
-	{ INFO("mt35xu512aba", 0x2c5b1a, 0,  128 * 1024,  512, USE_FSR | SPI_NOR_4B_OPCODES) },
-	{ INFO("mt35xu02g",  0x2c5b1c, 0, 128 * 1024,  2048, USE_FSR | SPI_NOR_4B_OPCODES) },
+	{ INFO("mt35xu512aba", 0x2c5b1a, 0,  128 * 1024,  512, USE_FSR | SPI_NOR_OCTAL_READ | SPI_NOR_4B_OPCODES) },
+	{ INFO("mt35xu02g",  0x2c5b1c, 0, 128 * 1024,  2048, USE_FSR | SPI_NOR_OCTAL_READ | SPI_NOR_4B_OPCODES) },
 #endif
 #ifdef CONFIG_SPI_FLASH_SPANSION	/* SPANSION */
 	/* Spansion/Cypress -- single (large) sector size only, at least
@@ -192,9 +193,10 @@
 	 */
 	{ INFO("s25sl032p",  0x010215, 0x4d00,  64 * 1024,  64, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ INFO("s25sl064p",  0x010216, 0x4d00,  64 * 1024, 128, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
-	{ INFO("s25fl256s0", 0x010219, 0x4d00, 256 * 1024, 128, USE_CLSR) },
+	{ INFO("s25fl256s0", 0x010219, 0x4d00, 256 * 1024, 128, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
 	{ INFO("s25fl256s1", 0x010219, 0x4d01,  64 * 1024, 512, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
-	{ INFO6("s25fl512s",  0x010220, 0x4d0081, 256 * 1024, 256, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
+	{ INFO6("s25fl512s",  0x010220, 0x4d0080, 256 * 1024, 256, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
+	{ INFO6("s25fs512s",  0x010220, 0x4d0081, 256 * 1024, 256, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
 	{ INFO("s25fl512s_256k",  0x010220, 0x4d00, 256 * 1024, 256, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
 	{ INFO("s25fl512s_64k",  0x010220, 0x4d01, 64 * 1024, 1024, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
 	{ INFO("s25fl512s_512k", 0x010220, 0x4f00, 256 * 1024, 256, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | USE_CLSR) },
diff --git a/drivers/rtc/pcf2127.c b/drivers/rtc/pcf2127.c
index f695350..b34ed63 100644
--- a/drivers/rtc/pcf2127.c
+++ b/drivers/rtc/pcf2127.c
@@ -56,7 +56,7 @@
 	buf[i++] = tm->tm_wday & 0x07;
 
 	/* month, 1 - 12 */
-	buf[i++] = bin2bcd(tm->tm_mon + 1);
+	buf[i++] = bin2bcd(tm->tm_mon);
 
 	/* year */
 	buf[i++] = bin2bcd(tm->tm_year % 100);
@@ -83,7 +83,7 @@
 	tm->tm_min  = bcd2bin(buf[PCF2127_REG_MN] & 0x7F);
 	tm->tm_hour = bcd2bin(buf[PCF2127_REG_HR] & 0x3F);
 	tm->tm_mday = bcd2bin(buf[PCF2127_REG_DM] & 0x3F);
-	tm->tm_mon  = bcd2bin(buf[PCF2127_REG_MO] & 0x1F) - 1;
+	tm->tm_mon  = bcd2bin(buf[PCF2127_REG_MO] & 0x1F);
 	tm->tm_year = bcd2bin(buf[PCF2127_REG_YR]) + 1900;
 	if (tm->tm_year < 1970)
 		tm->tm_year += 100;	/* assume we are in 1970...2069 */
diff --git a/drivers/spi/cadence_qspi.c b/drivers/spi/cadence_qspi.c
index 83b114f..994a594 100644
--- a/drivers/spi/cadence_qspi.c
+++ b/drivers/spi/cadence_qspi.c
@@ -166,11 +166,28 @@
 {
 	struct cadence_spi_platdata *plat = bus->platdata;
 	struct cadence_spi_priv *priv = dev_get_priv(bus);
+	struct clk clk;
 	int ret;
 
 	priv->regbase = plat->regbase;
 	priv->ahbbase = plat->ahbbase;
 
+	if (plat->ref_clk_hz == 0) {
+		ret = clk_get_by_index(bus, 0, &clk);
+		if (ret) {
+#ifdef CONFIG_CQSPI_REF_CLK
+			plat->ref_clk_hz = CONFIG_CQSPI_REF_CLK;
+#else
+			return ret;
+#endif
+		} else {
+			plat->ref_clk_hz = clk_get_rate(&clk);
+			clk_free(&clk);
+			if (IS_ERR_VALUE(plat->ref_clk_hz))
+				return plat->ref_clk_hz;
+		}
+	}
+
 	ret = reset_get_bulk(bus, &priv->resets);
 	if (ret)
 		dev_warn(bus, "Can't get reset: %d\n", ret);
@@ -268,8 +285,6 @@
 {
 	struct cadence_spi_platdata *plat = bus->platdata;
 	ofnode subnode;
-	struct clk clk;
-	int ret;
 
 	plat->regbase = (void *)devfdt_get_addr_index(bus, 0);
 	plat->ahbbase = (void *)devfdt_get_addr_size_index(bus, 1,
@@ -305,20 +320,6 @@
 	plat->tchsh_ns = ofnode_read_u32_default(subnode, "cdns,tchsh-ns", 20);
 	plat->tslch_ns = ofnode_read_u32_default(subnode, "cdns,tslch-ns", 20);
 
-	ret = clk_get_by_index(bus, 0, &clk);
-	if (ret) {
-#ifdef CONFIG_CQSPI_REF_CLK
-		plat->ref_clk_hz = CONFIG_CQSPI_REF_CLK;
-#else
-		return ret;
-#endif
-	} else {
-		plat->ref_clk_hz = clk_get_rate(&clk);
-		clk_free(&clk);
-		if (IS_ERR_VALUE(plat->ref_clk_hz))
-			return plat->ref_clk_hz;
-	}
-
 	debug("%s: regbase=%p ahbbase=%p max-frequency=%d page-size=%d\n",
 	      __func__, plat->regbase, plat->ahbbase, plat->max_hz,
 	      plat->page_size);
diff --git a/drivers/spi/fsl_qspi.c b/drivers/spi/fsl_qspi.c
index 8e2a09d..ee2c8b6 100644
--- a/drivers/spi/fsl_qspi.c
+++ b/drivers/spi/fsl_qspi.c
@@ -1,1142 +1,781 @@
 // SPDX-License-Identifier: GPL-2.0+
+
 /*
- * Copyright 2013-2015 Freescale Semiconductor, Inc.
+ * Freescale QuadSPI driver.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ * Copyright (C) 2018 Bootlin
+ * Copyright (C) 2018 exceet electronics GmbH
+ * Copyright (C) 2018 Kontron Electronics GmbH
+ * Copyright 2019-2020 NXP
  *
- * Freescale Quad Serial Peripheral Interface (QSPI) driver
+ * This driver is a ported version of Linux Freescale QSPI driver taken from
+ * v5.5-rc1 tag having following information.
+ *
+ * Transition to SPI MEM interface:
+ * Authors:
+ *     Boris Brezillon <bbrezillon@kernel.org>
+ *     Frieder Schrempf <frieder.schrempf@kontron.de>
+ *     Yogesh Gaur <yogeshnarayan.gaur@nxp.com>
+ *     Suresh Gupta <suresh.gupta@nxp.com>
+ *
+ * Based on the original fsl-quadspi.c spi-nor driver.
+ * Transition to spi-mem in spi-fsl-qspi.c
  */
 
 #include <common.h>
-#include <malloc.h>
-#include <spi.h>
 #include <asm/io.h>
-#include <linux/sizes.h>
-#include <linux/iopoll.h>
 #include <dm.h>
-#include <errno.h>
-#include <watchdog.h>
-#include <wait_bit.h>
-#include "fsl_qspi.h"
+#include <linux/iopoll.h>
+#include <linux/sizes.h>
+#include <linux/err.h>
+#include <spi.h>
+#include <spi-mem.h>
 
 DECLARE_GLOBAL_DATA_PTR;
 
-#define OFFSET_BITS_MASK	GENMASK(23, 0)
+/*
+ * The driver only uses one single LUT entry, that is updated on
+ * each call of exec_op(). Index 0 is preset at boot with a basic
+ * read operation, so let's use the last entry (15).
+ */
+#define	SEQID_LUT			15
 
-#define FLASH_STATUS_WEL	0x02
+/* Registers used by the driver */
+#define QUADSPI_MCR			0x00
+#define QUADSPI_MCR_RESERVED_MASK	GENMASK(19, 16)
+#define QUADSPI_MCR_MDIS_MASK		BIT(14)
+#define QUADSPI_MCR_CLR_TXF_MASK	BIT(11)
+#define QUADSPI_MCR_CLR_RXF_MASK	BIT(10)
+#define QUADSPI_MCR_DDR_EN_MASK		BIT(7)
+#define QUADSPI_MCR_END_CFG_MASK	GENMASK(3, 2)
+#define QUADSPI_MCR_SWRSTHD_MASK	BIT(1)
+#define QUADSPI_MCR_SWRSTSD_MASK	BIT(0)
 
-/* SEQID */
-#define SEQID_WREN		1
-#define SEQID_FAST_READ		2
-#define SEQID_RDSR		3
-#define SEQID_SE		4
-#define SEQID_CHIP_ERASE	5
-#define SEQID_PP		6
-#define SEQID_RDID		7
-#define SEQID_BE_4K		8
-#ifdef CONFIG_SPI_FLASH_BAR
-#define SEQID_BRRD		9
-#define SEQID_BRWR		10
-#define SEQID_RDEAR		11
-#define SEQID_WREAR		12
-#endif
-#define SEQID_WRAR		13
-#define SEQID_RDAR		14
+#define QUADSPI_IPCR			0x08
+#define QUADSPI_IPCR_SEQID(x)		((x) << 24)
+#define QUADSPI_FLSHCR			0x0c
+#define QUADSPI_FLSHCR_TCSS_MASK	GENMASK(3, 0)
+#define QUADSPI_FLSHCR_TCSH_MASK	GENMASK(11, 8)
+#define QUADSPI_FLSHCR_TDH_MASK		GENMASK(17, 16)
 
-/* QSPI CMD */
-#define QSPI_CMD_PP		0x02	/* Page program (up to 256 bytes) */
-#define QSPI_CMD_RDSR		0x05	/* Read status register */
-#define QSPI_CMD_WREN		0x06	/* Write enable */
-#define QSPI_CMD_FAST_READ	0x0b	/* Read data bytes (high frequency) */
-#define QSPI_CMD_BE_4K		0x20    /* 4K erase */
-#define QSPI_CMD_CHIP_ERASE	0xc7	/* Erase whole flash chip */
-#define QSPI_CMD_SE		0xd8	/* Sector erase (usually 64KiB) */
-#define QSPI_CMD_RDID		0x9f	/* Read JEDEC ID */
+#define QUADSPI_BUF3CR			0x1c
+#define QUADSPI_BUF3CR_ALLMST_MASK	BIT(31)
+#define QUADSPI_BUF3CR_ADATSZ(x)	((x) << 8)
+#define QUADSPI_BUF3CR_ADATSZ_MASK	GENMASK(15, 8)
 
-/* Used for Micron, winbond and Macronix flashes */
-#define	QSPI_CMD_WREAR		0xc5	/* EAR register write */
-#define	QSPI_CMD_RDEAR		0xc8	/* EAR reigster read */
+#define QUADSPI_BFGENCR			0x20
+#define QUADSPI_BFGENCR_SEQID(x)	((x) << 12)
 
-/* Used for Spansion flashes only. */
-#define	QSPI_CMD_BRRD		0x16	/* Bank register read */
-#define	QSPI_CMD_BRWR		0x17	/* Bank register write */
+#define QUADSPI_BUF0IND			0x30
+#define QUADSPI_BUF1IND			0x34
+#define QUADSPI_BUF2IND			0x38
+#define QUADSPI_SFAR			0x100
 
-/* Used for Spansion S25FS-S family flash only. */
-#define QSPI_CMD_RDAR		0x65	/* Read any device register */
-#define QSPI_CMD_WRAR		0x71	/* Write any device register */
+#define QUADSPI_SMPR			0x108
+#define QUADSPI_SMPR_DDRSMP_MASK	GENMASK(18, 16)
+#define QUADSPI_SMPR_FSDLY_MASK		BIT(6)
+#define QUADSPI_SMPR_FSPHS_MASK		BIT(5)
+#define QUADSPI_SMPR_HSENA_MASK		BIT(0)
 
-/* 4-byte address QSPI CMD - used on Spansion and some Macronix flashes */
-#define QSPI_CMD_FAST_READ_4B	0x0c    /* Read data bytes (high frequency) */
-#define QSPI_CMD_PP_4B		0x12    /* Page program (up to 256 bytes) */
-#define QSPI_CMD_SE_4B		0xdc    /* Sector erase (usually 64KiB) */
+#define QUADSPI_RBCT			0x110
+#define QUADSPI_RBCT_WMRK_MASK		GENMASK(4, 0)
+#define QUADSPI_RBCT_RXBRD_USEIPS	BIT(8)
 
-/* fsl_qspi_platdata flags */
-#define QSPI_FLAG_REGMAP_ENDIAN_BIG	BIT(0)
+#define QUADSPI_TBDR			0x154
 
-/* default SCK frequency, unit: HZ */
-#define FSL_QSPI_DEFAULT_SCK_FREQ	50000000
+#define QUADSPI_SR			0x15c
+#define QUADSPI_SR_IP_ACC_MASK		BIT(1)
+#define QUADSPI_SR_AHB_ACC_MASK		BIT(2)
 
-/* QSPI max chipselect signals number */
-#define FSL_QSPI_MAX_CHIPSELECT_NUM     4
+#define QUADSPI_FR			0x160
+#define QUADSPI_FR_TFF_MASK		BIT(0)
 
-/* Controller needs driver to swap endian */
-#define QUADSPI_QUIRK_SWAP_ENDIAN	BIT(0)
+#define QUADSPI_RSER			0x164
+#define QUADSPI_RSER_TFIE		BIT(0)
 
-enum fsl_qspi_devtype {
-	FSL_QUADSPI_VYBRID,
-	FSL_QUADSPI_IMX6SX,
-	FSL_QUADSPI_IMX6UL_7D,
-	FSL_QUADSPI_IMX7ULP,
-};
+#define QUADSPI_SPTRCLR			0x16c
+#define QUADSPI_SPTRCLR_IPPTRC		BIT(8)
+#define QUADSPI_SPTRCLR_BFPTRC		BIT(0)
 
-struct fsl_qspi_devtype_data {
-	enum fsl_qspi_devtype devtype;
-	u32 rxfifo;
-	u32 txfifo;
-	u32 ahb_buf_size;
-	u32 driver_data;
-};
+#define QUADSPI_SFA1AD			0x180
+#define QUADSPI_SFA2AD			0x184
+#define QUADSPI_SFB1AD			0x188
+#define QUADSPI_SFB2AD			0x18c
+#define QUADSPI_RBDR(x)			(0x200 + ((x) * 4))
 
-/**
- * struct fsl_qspi_platdata - platform data for Freescale QSPI
+#define QUADSPI_LUTKEY			0x300
+#define QUADSPI_LUTKEY_VALUE		0x5AF05AF0
+
+#define QUADSPI_LCKCR			0x304
+#define QUADSPI_LCKER_LOCK		BIT(0)
+#define QUADSPI_LCKER_UNLOCK		BIT(1)
+
+#define QUADSPI_LUT_BASE		0x310
+#define QUADSPI_LUT_OFFSET		(SEQID_LUT * 4 * 4)
+#define QUADSPI_LUT_REG(idx) \
+	(QUADSPI_LUT_BASE + QUADSPI_LUT_OFFSET + (idx) * 4)
+
+/* Instruction set for the LUT register */
+#define LUT_STOP		0
+#define LUT_CMD			1
+#define LUT_ADDR		2
+#define LUT_DUMMY		3
+#define LUT_MODE		4
+#define LUT_MODE2		5
+#define LUT_MODE4		6
+#define LUT_FSL_READ		7
+#define LUT_FSL_WRITE		8
+#define LUT_JMP_ON_CS		9
+#define LUT_ADDR_DDR		10
+#define LUT_MODE_DDR		11
+#define LUT_MODE2_DDR		12
+#define LUT_MODE4_DDR		13
+#define LUT_FSL_READ_DDR	14
+#define LUT_FSL_WRITE_DDR	15
+#define LUT_DATA_LEARN		16
+
+/*
+ * The PAD definitions for LUT register.
  *
- * @flags: Flags for QSPI QSPI_FLAG_...
- * @speed_hz: Default SCK frequency
- * @reg_base: Base address of QSPI registers
- * @amba_base: Base address of QSPI memory mapping
- * @amba_total_size: size of QSPI memory mapping
- * @flash_num: Number of active slave devices
- * @num_chipselect: Number of QSPI chipselect signals
+ * The pad stands for the number of IO lines [0:3].
+ * For example, the quad read needs four IO lines,
+ * so you should use LUT_PAD(4).
  */
-struct fsl_qspi_platdata {
-	u32 flags;
-	u32 speed_hz;
-	fdt_addr_t reg_base;
-	fdt_addr_t amba_base;
-	fdt_size_t amba_total_size;
-	u32 flash_num;
-	u32 num_chipselect;
-};
+#define LUT_PAD(x) (fls(x) - 1)
 
-/**
- * struct fsl_qspi_priv - private data for Freescale QSPI
+/*
+ * Macro for constructing the LUT entries with the following
+ * register layout:
  *
- * @flags: Flags for QSPI QSPI_FLAG_...
- * @bus_clk: QSPI input clk frequency
- * @speed_hz: Default SCK frequency
- * @cur_seqid: current LUT table sequence id
- * @sf_addr: flash access offset
- * @amba_base: Base address of QSPI memory mapping of every CS
- * @amba_total_size: size of QSPI memory mapping
- * @cur_amba_base: Base address of QSPI memory mapping of current CS
- * @flash_num: Number of active slave devices
- * @num_chipselect: Number of QSPI chipselect signals
- * @regs: Point to QSPI register structure for I/O access
+ *  ---------------------------------------------------
+ *  | INSTR1 | PAD1 | OPRND1 | INSTR0 | PAD0 | OPRND0 |
+ *  ---------------------------------------------------
+ */
+#define LUT_DEF(idx, ins, pad, opr)					\
+	((((ins) << 10) | ((pad) << 8) | (opr)) << (((idx) % 2) * 16))
+
+/* Controller needs driver to swap endianness */
+#define QUADSPI_QUIRK_SWAP_ENDIAN	BIT(0)
+
+/* Controller needs 4x internal clock */
+#define QUADSPI_QUIRK_4X_INT_CLK	BIT(1)
+
+/*
+ * TKT253890, the controller needs the driver to fill the txfifo with
+ * 16 bytes at least to trigger a data transfer, even though the extra
+ * data won't be transferred.
+ */
+#define QUADSPI_QUIRK_TKT253890		BIT(2)
+
+/* TKT245618, the controller cannot wake up from wait mode */
+#define QUADSPI_QUIRK_TKT245618		BIT(3)
+
+/*
+ * Controller adds QSPI_AMBA_BASE (base address of the mapped memory)
+ * internally. No need to add it when setting SFXXAD and SFAR registers
+ */
+#define QUADSPI_QUIRK_BASE_INTERNAL	BIT(4)
+
+/*
+ * Controller uses TDH bits in register QUADSPI_FLSHCR.
+ * They need to be set in accordance with the DDR/SDR mode.
  */
-struct fsl_qspi_priv {
-	u32 flags;
-	u32 bus_clk;
-	u32 speed_hz;
-	u32 cur_seqid;
-	u32 sf_addr;
-	u32 amba_base[FSL_QSPI_MAX_CHIPSELECT_NUM];
-	u32 amba_total_size;
-	u32 cur_amba_base;
-	u32 flash_num;
-	u32 num_chipselect;
-	struct fsl_qspi_regs *regs;
-	struct fsl_qspi_devtype_data *devtype_data;
+#define QUADSPI_QUIRK_USE_TDH_SETTING	BIT(5)
+
+struct fsl_qspi_devtype_data {
+	unsigned int rxfifo;
+	unsigned int txfifo;
+	unsigned int ahb_buf_size;
+	unsigned int quirks;
+	bool little_endian;
 };
 
 static const struct fsl_qspi_devtype_data vybrid_data = {
-	.devtype = FSL_QUADSPI_VYBRID,
-	.rxfifo = 128,
-	.txfifo = 64,
-	.ahb_buf_size = 1024,
-	.driver_data = QUADSPI_QUIRK_SWAP_ENDIAN,
+	.rxfifo = SZ_128,
+	.txfifo = SZ_64,
+	.ahb_buf_size = SZ_1K,
+	.quirks = QUADSPI_QUIRK_SWAP_ENDIAN,
+	.little_endian = true,
 };
 
 static const struct fsl_qspi_devtype_data imx6sx_data = {
-	.devtype = FSL_QUADSPI_IMX6SX,
-	.rxfifo = 128,
-	.txfifo = 512,
-	.ahb_buf_size = 1024,
-	.driver_data = 0,
+	.rxfifo = SZ_128,
+	.txfifo = SZ_512,
+	.ahb_buf_size = SZ_1K,
+	.quirks = QUADSPI_QUIRK_4X_INT_CLK | QUADSPI_QUIRK_TKT245618,
+	.little_endian = true,
 };
 
-static const struct fsl_qspi_devtype_data imx6ul_7d_data = {
-	.devtype = FSL_QUADSPI_IMX6UL_7D,
-	.rxfifo = 128,
-	.txfifo = 512,
-	.ahb_buf_size = 1024,
-	.driver_data = 0,
+static const struct fsl_qspi_devtype_data imx7d_data = {
+	.rxfifo = SZ_128,
+	.txfifo = SZ_512,
+	.ahb_buf_size = SZ_1K,
+	.quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK |
+		  QUADSPI_QUIRK_USE_TDH_SETTING,
+	.little_endian = true,
 };
 
-static const struct fsl_qspi_devtype_data imx7ulp_data = {
-	.devtype = FSL_QUADSPI_IMX7ULP,
-	.rxfifo = 64,
-	.txfifo = 64,
-	.ahb_buf_size = 128,
-	.driver_data = 0,
+static const struct fsl_qspi_devtype_data imx6ul_data = {
+	.rxfifo = SZ_128,
+	.txfifo = SZ_512,
+	.ahb_buf_size = SZ_1K,
+	.quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK |
+		  QUADSPI_QUIRK_USE_TDH_SETTING,
+	.little_endian = true,
 };
 
-static u32 qspi_read32(u32 flags, u32 *addr)
+static const struct fsl_qspi_devtype_data ls1021a_data = {
+	.rxfifo = SZ_128,
+	.txfifo = SZ_64,
+	.ahb_buf_size = SZ_1K,
+	.quirks = 0,
+	.little_endian = false,
+};
+
+static const struct fsl_qspi_devtype_data ls1088a_data = {
+	.rxfifo = SZ_128,
+	.txfifo = SZ_128,
+	.ahb_buf_size = SZ_1K,
+	.quirks = QUADSPI_QUIRK_TKT253890,
+	.little_endian = true,
+};
+
+static const struct fsl_qspi_devtype_data ls2080a_data = {
+	.rxfifo = SZ_128,
+	.txfifo = SZ_64,
+	.ahb_buf_size = SZ_1K,
+	.quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_BASE_INTERNAL,
+	.little_endian = true,
+};
+
+struct fsl_qspi {
+	struct udevice *dev;
+	void __iomem *iobase;
+	void __iomem *ahb_addr;
+	u32 memmap_phy;
+	const struct fsl_qspi_devtype_data *devtype_data;
+	int selected;
+};
+
+static inline int needs_swap_endian(struct fsl_qspi *q)
 {
-	return flags & QSPI_FLAG_REGMAP_ENDIAN_BIG ?
-		in_be32(addr) : in_le32(addr);
+	return q->devtype_data->quirks & QUADSPI_QUIRK_SWAP_ENDIAN;
 }
 
-static void qspi_write32(u32 flags, u32 *addr, u32 val)
+static inline int needs_4x_clock(struct fsl_qspi *q)
 {
-	flags & QSPI_FLAG_REGMAP_ENDIAN_BIG ?
-		out_be32(addr, val) : out_le32(addr, val);
+	return q->devtype_data->quirks & QUADSPI_QUIRK_4X_INT_CLK;
 }
 
-static inline int is_controller_busy(const struct fsl_qspi_priv *priv)
+static inline int needs_fill_txfifo(struct fsl_qspi *q)
 {
-	u32 val;
-	u32 mask = QSPI_SR_BUSY_MASK | QSPI_SR_AHB_ACC_MASK |
-		   QSPI_SR_IP_ACC_MASK;
-
-	if (priv->flags & QSPI_FLAG_REGMAP_ENDIAN_BIG)
-		mask = (u32)cpu_to_be32(mask);
-
-	return readl_poll_timeout(&priv->regs->sr, val, !(val & mask), 1000);
+	return q->devtype_data->quirks & QUADSPI_QUIRK_TKT253890;
 }
 
-/* QSPI support swapping the flash read/write data
- * in hardware for LS102xA, but not for VF610 */
-static inline u32 qspi_endian_xchg(struct fsl_qspi_priv *priv, u32 data)
+static inline int needs_wakeup_wait_mode(struct fsl_qspi *q)
 {
-	if (priv->devtype_data->driver_data & QUADSPI_QUIRK_SWAP_ENDIAN)
-		return swab32(data);
-	else
-		return data;
+	return q->devtype_data->quirks & QUADSPI_QUIRK_TKT245618;
 }
 
-static void qspi_set_lut(struct fsl_qspi_priv *priv)
+static inline int needs_amba_base_offset(struct fsl_qspi *q)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 lut_base;
+	return !(q->devtype_data->quirks & QUADSPI_QUIRK_BASE_INTERNAL);
+}
 
-	/* Unlock the LUT */
-	qspi_write32(priv->flags, &regs->lutkey, LUT_KEY_VALUE);
-	qspi_write32(priv->flags, &regs->lckcr, QSPI_LCKCR_UNLOCK);
+static inline int needs_tdh_setting(struct fsl_qspi *q)
+{
+	return q->devtype_data->quirks & QUADSPI_QUIRK_USE_TDH_SETTING;
+}
 
-	/* Write Enable */
-	lut_base = SEQID_WREN * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_WREN) |
-		PAD0(LUT_PAD1) | INSTR0(LUT_CMD));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 2], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 3], 0);
+/*
+ * An IC bug makes it necessary to rearrange the 32-bit data.
+ * Later chips, such as IMX6SLX, have fixed this bug.
+ */
+static inline u32 fsl_qspi_endian_xchg(struct fsl_qspi *q, u32 a)
+{
+	return needs_swap_endian(q) ? __swab32(a) : a;
+}
 
-	/* Fast Read */
-	lut_base = SEQID_FAST_READ * 4;
-#ifdef CONFIG_SPI_FLASH_BAR
-	qspi_write32(priv->flags, &regs->lut[lut_base],
-		     OPRND0(QSPI_CMD_FAST_READ) | PAD0(LUT_PAD1) |
-		     INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-#else
-	if (FSL_QSPI_FLASH_SIZE  <= SZ_16M)
-		qspi_write32(priv->flags, &regs->lut[lut_base],
-			     OPRND0(QSPI_CMD_FAST_READ) | PAD0(LUT_PAD1) |
-			     INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-			     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+/*
+ * R/W functions for big- or little-endian registers:
+ * The QSPI controller's endianness is independent of
+ * the CPU core's endianness. So far, although the CPU
+ * core is little-endian the QSPI controller can use
+ * big-endian or little-endian.
+ */
+static void qspi_writel(struct fsl_qspi *q, u32 val, void __iomem *addr)
+{
+	if (q->devtype_data->little_endian)
+		out_le32(addr, val);
 	else
-		qspi_write32(priv->flags, &regs->lut[lut_base],
-			     OPRND0(QSPI_CMD_FAST_READ_4B) |
-			     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) |
-			     OPRND1(ADDR32BIT) | PAD1(LUT_PAD1) |
-			     INSTR1(LUT_ADDR));
-#endif
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1],
-		     OPRND0(8) | PAD0(LUT_PAD1) | INSTR0(LUT_DUMMY) |
-		     OPRND1(priv->devtype_data->rxfifo) | PAD1(LUT_PAD1) |
-		     INSTR1(LUT_READ));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 2], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 3], 0);
+		out_be32(addr, val);
+}
 
-	/* Read Status */
-	lut_base = SEQID_RDSR * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_RDSR) |
-		PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(1) |
-		PAD1(LUT_PAD1) | INSTR1(LUT_READ));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 2], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 3], 0);
+static u32 qspi_readl(struct fsl_qspi *q, void __iomem *addr)
+{
+	if (q->devtype_data->little_endian)
+		return in_le32(addr);
 
-	/* Erase a sector */
-	lut_base = SEQID_SE * 4;
-#ifdef CONFIG_SPI_FLASH_BAR
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_SE) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-#else
-	if (FSL_QSPI_FLASH_SIZE  <= SZ_16M)
-		qspi_write32(priv->flags, &regs->lut[lut_base],
-			     OPRND0(QSPI_CMD_SE) | PAD0(LUT_PAD1) |
-			     INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-			     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-	else
-		qspi_write32(priv->flags, &regs->lut[lut_base],
-			     OPRND0(QSPI_CMD_SE_4B) | PAD0(LUT_PAD1) |
-			     INSTR0(LUT_CMD) | OPRND1(ADDR32BIT) |
-			     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-#endif
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 2], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 3], 0);
+	return in_be32(addr);
+}
 
-	/* Erase the whole chip */
-	lut_base = SEQID_CHIP_ERASE * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base],
-		     OPRND0(QSPI_CMD_CHIP_ERASE) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 2], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 3], 0);
+static int fsl_qspi_check_buswidth(struct fsl_qspi *q, u8 width)
+{
+	switch (width) {
+	case 1:
+	case 2:
+	case 4:
+		return 0;
+	}
 
-	/* Page Program */
-	lut_base = SEQID_PP * 4;
-#ifdef CONFIG_SPI_FLASH_BAR
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_PP) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-#else
-	if (FSL_QSPI_FLASH_SIZE  <= SZ_16M)
-		qspi_write32(priv->flags, &regs->lut[lut_base],
-			     OPRND0(QSPI_CMD_PP) | PAD0(LUT_PAD1) |
-			     INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-			     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-	else
-		qspi_write32(priv->flags, &regs->lut[lut_base],
-			     OPRND0(QSPI_CMD_PP_4B) | PAD0(LUT_PAD1) |
-			     INSTR0(LUT_CMD) | OPRND1(ADDR32BIT) |
-			     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-#endif
-	/* Use IDATSZ in IPCR to determine the size and here set 0. */
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1], OPRND0(0) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_WRITE));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 2], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 3], 0);
+	return -ENOTSUPP;
+}
 
-	/* READ ID */
-	lut_base = SEQID_RDID * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_RDID) |
-		PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(8) |
-		PAD1(LUT_PAD1) | INSTR1(LUT_READ));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 2], 0);
-	qspi_write32(priv->flags, &regs->lut[lut_base + 3], 0);
+static bool fsl_qspi_supports_op(struct spi_slave *slave,
+				 const struct spi_mem_op *op)
+{
+	struct fsl_qspi *q = dev_get_priv(slave->dev->parent);
+	int ret;
 
-	/* SUB SECTOR 4K ERASE */
-	lut_base = SEQID_BE_4K * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_BE_4K) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+	ret = fsl_qspi_check_buswidth(q, op->cmd.buswidth);
 
-#ifdef CONFIG_SPI_FLASH_BAR
-	/*
-	 * BRRD BRWR RDEAR WREAR are all supported, because it is hard to
-	 * dynamically check whether to set BRRD BRWR or RDEAR WREAR during
-	 * initialization.
-	 */
-	lut_base = SEQID_BRRD * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_BRRD) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(1) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_READ));
+	if (op->addr.nbytes)
+		ret |= fsl_qspi_check_buswidth(q, op->addr.buswidth);
 
-	lut_base = SEQID_BRWR * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_BRWR) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(1) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_WRITE));
+	if (op->dummy.nbytes)
+		ret |= fsl_qspi_check_buswidth(q, op->dummy.buswidth);
 
-	lut_base = SEQID_RDEAR * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_RDEAR) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(1) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_READ));
+	if (op->data.nbytes)
+		ret |= fsl_qspi_check_buswidth(q, op->data.buswidth);
 
-	lut_base = SEQID_WREAR * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base], OPRND0(QSPI_CMD_WREAR) |
-		     PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(1) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_WRITE));
-#endif
+	if (ret)
+		return false;
 
 	/*
-	 * Read any device register.
-	 * Used for Spansion S25FS-S family flash only.
+	 * The number of instructions needed for the op, needs
+	 * to fit into a single LUT entry.
 	 */
-	lut_base = SEQID_RDAR * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base],
-		     OPRND0(QSPI_CMD_RDAR) | PAD0(LUT_PAD1) |
-		     INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1],
-		     OPRND0(8) | PAD0(LUT_PAD1) | INSTR0(LUT_DUMMY) |
-		     OPRND1(1) | PAD1(LUT_PAD1) |
-		     INSTR1(LUT_READ));
+	if (op->addr.nbytes +
+	   (op->dummy.nbytes ? 1 : 0) +
+	   (op->data.nbytes ? 1 : 0) > 6)
+		return false;
 
-	/*
-	 * Write any device register.
-	 * Used for Spansion S25FS-S family flash only.
-	 */
-	lut_base = SEQID_WRAR * 4;
-	qspi_write32(priv->flags, &regs->lut[lut_base],
-		     OPRND0(QSPI_CMD_WRAR) | PAD0(LUT_PAD1) |
-		     INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
-		     PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
-	qspi_write32(priv->flags, &regs->lut[lut_base + 1],
-		     OPRND0(1) | PAD0(LUT_PAD1) | INSTR0(LUT_WRITE));
+	/* Max 64 dummy clock cycles supported */
+	if (op->dummy.nbytes &&
+	    (op->dummy.nbytes * 8 / op->dummy.buswidth > 64))
+		return false;
 
-	/* Lock the LUT */
-	qspi_write32(priv->flags, &regs->lutkey, LUT_KEY_VALUE);
-	qspi_write32(priv->flags, &regs->lckcr, QSPI_LCKCR_LOCK);
+	/* Max data length, check controller limits and alignment */
+	if (op->data.dir == SPI_MEM_DATA_IN &&
+	    (op->data.nbytes > q->devtype_data->ahb_buf_size ||
+	     (op->data.nbytes > q->devtype_data->rxfifo - 4 &&
+	      !IS_ALIGNED(op->data.nbytes, 8))))
+		return false;
+
+	if (op->data.dir == SPI_MEM_DATA_OUT &&
+	    op->data.nbytes > q->devtype_data->txfifo)
+		return false;
+
+	return true;
 }
 
-#if defined(CONFIG_SYS_FSL_QSPI_AHB)
-/*
- * If we have changed the content of the flash by writing or erasing,
- * we need to invalidate the AHB buffer. If we do not do so, we may read out
- * the wrong data. The spec tells us reset the AHB domain and Serial Flash
- * domain at the same time.
- */
-static inline void qspi_ahb_invalid(struct fsl_qspi_priv *priv)
+static void fsl_qspi_prepare_lut(struct fsl_qspi *q,
+				 const struct spi_mem_op *op)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 reg;
+	void __iomem *base = q->iobase;
+	u32 lutval[4] = {};
+	int lutidx = 1, i;
 
-	reg = qspi_read32(priv->flags, &regs->mcr);
-	reg |= QSPI_MCR_SWRSTHD_MASK | QSPI_MCR_SWRSTSD_MASK;
-	qspi_write32(priv->flags, &regs->mcr, reg);
+	lutval[0] |= LUT_DEF(0, LUT_CMD, LUT_PAD(op->cmd.buswidth),
+			     op->cmd.opcode);
 
 	/*
-	 * The minimum delay : 1 AHB + 2 SFCK clocks.
-	 * Delay 1 us is enough.
+	 * For some unknown reason, using LUT_ADDR doesn't work in some
+	 * cases (at least with only one byte long addresses), so
+	 * let's use LUT_MODE to write the address bytes one by one
 	 */
-	udelay(1);
-
-	reg &= ~(QSPI_MCR_SWRSTHD_MASK | QSPI_MCR_SWRSTSD_MASK);
-	qspi_write32(priv->flags, &regs->mcr, reg);
-}
+	for (i = 0; i < op->addr.nbytes; i++) {
+		u8 addrbyte = op->addr.val >> (8 * (op->addr.nbytes - i - 1));
 
-/* Read out the data from the AHB buffer. */
-static inline void qspi_ahb_read(struct fsl_qspi_priv *priv, u8 *rxbuf, int len)
-{
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 mcr_reg;
-	void *rx_addr;
-
-	mcr_reg = qspi_read32(priv->flags, &regs->mcr);
-
-	qspi_write32(priv->flags, &regs->mcr,
-		     QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
-		     mcr_reg);
+		lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_MODE,
+					      LUT_PAD(op->addr.buswidth),
+					      addrbyte);
+		lutidx++;
+	}
 
-	rx_addr = (void *)(uintptr_t)(priv->cur_amba_base + priv->sf_addr);
-	/* Read out the data directly from the AHB buffer. */
-	memcpy(rxbuf, rx_addr, len);
+	if (op->dummy.nbytes) {
+		lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_DUMMY,
+					      LUT_PAD(op->dummy.buswidth),
+					      op->dummy.nbytes * 8 /
+					      op->dummy.buswidth);
+		lutidx++;
+	}
 
-	qspi_write32(priv->flags, &regs->mcr, mcr_reg);
-}
+	if (op->data.nbytes) {
+		lutval[lutidx / 2] |= LUT_DEF(lutidx,
+					      op->data.dir == SPI_MEM_DATA_IN ?
+					      LUT_FSL_READ : LUT_FSL_WRITE,
+					      LUT_PAD(op->data.buswidth),
+					      0);
+		lutidx++;
+	}
 
-static void qspi_enable_ddr_mode(struct fsl_qspi_priv *priv)
-{
-	u32 reg, reg2;
-	struct fsl_qspi_regs *regs = priv->regs;
+	lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_STOP, 0, 0);
 
-	reg = qspi_read32(priv->flags, &regs->mcr);
-	/* Disable the module */
-	qspi_write32(priv->flags, &regs->mcr, reg | QSPI_MCR_MDIS_MASK);
+	/* unlock LUT */
+	qspi_writel(q, QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+	qspi_writel(q, QUADSPI_LCKER_UNLOCK, q->iobase + QUADSPI_LCKCR);
 
-	/* Set the Sampling Register for DDR */
-	reg2 = qspi_read32(priv->flags, &regs->smpr);
-	reg2 &= ~QSPI_SMPR_DDRSMP_MASK;
-	reg2 |= (2 << QSPI_SMPR_DDRSMP_SHIFT);
-	qspi_write32(priv->flags, &regs->smpr, reg2);
+	dev_dbg(q->dev, "CMD[%x] lutval[0:%x \t 1:%x \t 2:%x \t 3:%x]\n",
+		op->cmd.opcode, lutval[0], lutval[1], lutval[2], lutval[3]);
 
-	/* Enable the module again (enable the DDR too) */
-	reg |= QSPI_MCR_DDR_EN_MASK;
-	/* Enable bit 29 for imx6sx */
-	reg |= BIT(29);
-	qspi_write32(priv->flags, &regs->mcr, reg);
+	/* fill LUT */
+	for (i = 0; i < ARRAY_SIZE(lutval); i++)
+		qspi_writel(q, lutval[i], base + QUADSPI_LUT_REG(i));
 
-	/* Enable the TDH to 1 for some platforms like imx6ul, imx7d, etc
-	 * These two bits are reserved on other platforms
-	 */
-	reg = qspi_read32(priv->flags, &regs->flshcr);
-	reg &= ~(BIT(17));
-	reg |= BIT(16);
-	qspi_write32(priv->flags, &regs->flshcr, reg);
+	/* lock LUT */
+	qspi_writel(q, QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+	qspi_writel(q, QUADSPI_LCKER_LOCK, q->iobase + QUADSPI_LCKCR);
 }
 
 /*
- * There are two different ways to read out the data from the flash:
- *  the "IP Command Read" and the "AHB Command Read".
- *
- * The IC guy suggests we use the "AHB Command Read" which is faster
- * then the "IP Command Read". (What's more is that there is a bug in
- * the "IP Command Read" in the Vybrid.)
- *
- * After we set up the registers for the "AHB Command Read", we can use
- * the memcpy to read the data directly. A "missed" access to the buffer
- * causes the controller to clear the buffer, and use the sequence pointed
- * by the QUADSPI_BFGENCR[SEQID] to initiate a read from the flash.
+ * If we have changed the content of the flash by writing or erasing, or if we
+ * read from flash with a different offset into the page buffer, we need to
+ * invalidate the AHB buffer. If we do not do so, we may read out the wrong
+ * data. The spec tells us reset the AHB domain and Serial Flash domain at
+ * the same time.
  */
-static void qspi_init_ahb_read(struct fsl_qspi_priv *priv)
+static void fsl_qspi_invalidate(struct fsl_qspi *q)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-
-	/* AHB configuration for access buffer 0/1/2 .*/
-	qspi_write32(priv->flags, &regs->buf0cr, QSPI_BUFXCR_INVALID_MSTRID);
-	qspi_write32(priv->flags, &regs->buf1cr, QSPI_BUFXCR_INVALID_MSTRID);
-	qspi_write32(priv->flags, &regs->buf2cr, QSPI_BUFXCR_INVALID_MSTRID);
-	qspi_write32(priv->flags, &regs->buf3cr, QSPI_BUF3CR_ALLMST_MASK |
-		     ((priv->devtype_data->ahb_buf_size >> 3) << QSPI_BUF3CR_ADATSZ_SHIFT));
+	u32 reg;
 
-	/* We only use the buffer3 */
-	qspi_write32(priv->flags, &regs->buf0ind, 0);
-	qspi_write32(priv->flags, &regs->buf1ind, 0);
-	qspi_write32(priv->flags, &regs->buf2ind, 0);
+	reg = qspi_readl(q, q->iobase + QUADSPI_MCR);
+	reg |= QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK;
+	qspi_writel(q, reg, q->iobase + QUADSPI_MCR);
 
 	/*
-	 * Set the default lut sequence for AHB Read.
-	 * Parallel mode is disabled.
+	 * The minimum delay : 1 AHB + 2 SFCK clocks.
+	 * Delay 1 us is enough.
 	 */
-	qspi_write32(priv->flags, &regs->bfgencr,
-		     SEQID_FAST_READ << QSPI_BFGENCR_SEQID_SHIFT);
+	udelay(1);
 
-	/*Enable DDR Mode*/
-	qspi_enable_ddr_mode(priv);
+	reg &= ~(QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK);
+	qspi_writel(q, reg, q->iobase + QUADSPI_MCR);
 }
-#endif
 
-#ifdef CONFIG_SPI_FLASH_BAR
-/* Bank register read/write, EAR register read/write */
-static void qspi_op_rdbank(struct fsl_qspi_priv *priv, u8 *rxbuf, u32 len)
+static void fsl_qspi_select_mem(struct fsl_qspi *q, struct spi_slave *slave)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 reg, mcr_reg, data, seqid;
-
-	mcr_reg = qspi_read32(priv->flags, &regs->mcr);
-	qspi_write32(priv->flags, &regs->mcr,
-		     QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
-		     mcr_reg);
-	qspi_write32(priv->flags, &regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
-
-	qspi_write32(priv->flags, &regs->sfar, priv->cur_amba_base);
+	struct dm_spi_slave_platdata *plat =
+		dev_get_parent_platdata(slave->dev);
 
-	if (priv->cur_seqid == QSPI_CMD_BRRD)
-		seqid = SEQID_BRRD;
-	else
-		seqid = SEQID_RDEAR;
-
-	qspi_write32(priv->flags, &regs->ipcr,
-		     (seqid << QSPI_IPCR_SEQID_SHIFT) | len);
-
-	/* Wait previous command complete */
-	while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-		;
-
-	while (1) {
-		WATCHDOG_RESET();
+	if (q->selected == plat->cs)
+		return;
 
-		reg = qspi_read32(priv->flags, &regs->rbsr);
-		if (reg & QSPI_RBSR_RDBFL_MASK) {
-			data = qspi_read32(priv->flags, &regs->rbdr[0]);
-			data = qspi_endian_xchg(priv, data);
-			memcpy(rxbuf, &data, len);
-			qspi_write32(priv->flags, &regs->mcr,
-				     qspi_read32(priv->flags, &regs->mcr) |
-				     QSPI_MCR_CLR_RXF_MASK);
-			break;
-		}
-	}
-
-	qspi_write32(priv->flags, &regs->mcr, mcr_reg);
+	q->selected = plat->cs;
+	fsl_qspi_invalidate(q);
 }
-#endif
 
-static void qspi_op_rdid(struct fsl_qspi_priv *priv, u32 *rxbuf, u32 len)
+static void fsl_qspi_read_ahb(struct fsl_qspi *q, const struct spi_mem_op *op)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 mcr_reg, rbsr_reg, data, size;
-	int i;
-
-	mcr_reg = qspi_read32(priv->flags, &regs->mcr);
-	qspi_write32(priv->flags, &regs->mcr,
-		     QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
-		     mcr_reg);
-	qspi_write32(priv->flags, &regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
-
-	qspi_write32(priv->flags, &regs->sfar, priv->cur_amba_base);
-
-	qspi_write32(priv->flags, &regs->ipcr,
-		     (SEQID_RDID << QSPI_IPCR_SEQID_SHIFT) | 0);
-	while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-		;
-
-	i = 0;
-	while ((priv->devtype_data->rxfifo >= len) && (len > 0)) {
-		WATCHDOG_RESET();
-
-		rbsr_reg = qspi_read32(priv->flags, &regs->rbsr);
-		if (rbsr_reg & QSPI_RBSR_RDBFL_MASK) {
-			data = qspi_read32(priv->flags, &regs->rbdr[i]);
-			data = qspi_endian_xchg(priv, data);
-			size = (len < 4) ? len : 4;
-			memcpy(rxbuf, &data, size);
-			len -= size;
-			rxbuf++;
-			i++;
-		}
-	}
-
-	qspi_write32(priv->flags, &regs->mcr, mcr_reg);
+	memcpy_fromio(op->data.buf.in,
+		      q->ahb_addr + q->selected * q->devtype_data->ahb_buf_size,
+		      op->data.nbytes);
 }
 
-/* If not use AHB read, read data from ip interface */
-static void qspi_op_read(struct fsl_qspi_priv *priv, u32 *rxbuf, u32 len)
+static void fsl_qspi_fill_txfifo(struct fsl_qspi *q,
+				 const struct spi_mem_op *op)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 mcr_reg, data;
-	int i, size;
-	u32 to_or_from;
-	u32 seqid;
-
-	if (priv->cur_seqid == QSPI_CMD_RDAR)
-		seqid = SEQID_RDAR;
-	else
-		seqid = SEQID_FAST_READ;
-
-	mcr_reg = qspi_read32(priv->flags, &regs->mcr);
-	qspi_write32(priv->flags, &regs->mcr,
-		     QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
-		     mcr_reg);
-	qspi_write32(priv->flags, &regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
-
-	to_or_from = priv->sf_addr + priv->cur_amba_base;
-
-	while (len > 0) {
-		WATCHDOG_RESET();
-
-		qspi_write32(priv->flags, &regs->sfar, to_or_from);
-
-		size = (len > priv->devtype_data->rxfifo) ?
-			priv->devtype_data->rxfifo : len;
-
-		qspi_write32(priv->flags, &regs->ipcr,
-			     (seqid << QSPI_IPCR_SEQID_SHIFT) |
-			     size);
-		while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-			;
+	void __iomem *base = q->iobase;
+	int i;
+	u32 val;
 
-		to_or_from += size;
-		len -= size;
+	for (i = 0; i < ALIGN_DOWN(op->data.nbytes, 4); i += 4) {
+		memcpy(&val, op->data.buf.out + i, 4);
+		val = fsl_qspi_endian_xchg(q, val);
+		qspi_writel(q, val, base + QUADSPI_TBDR);
+	}
 
-		i = 0;
-		while ((priv->devtype_data->rxfifo >= size) && (size > 0)) {
-			data = qspi_read32(priv->flags, &regs->rbdr[i]);
-			data = qspi_endian_xchg(priv, data);
-			if (size < 4)
-				memcpy(rxbuf, &data, size);
-			else
-				memcpy(rxbuf, &data, 4);
-			rxbuf++;
-			size -= 4;
-			i++;
-		}
-		qspi_write32(priv->flags, &regs->mcr,
-			     qspi_read32(priv->flags, &regs->mcr) |
-			     QSPI_MCR_CLR_RXF_MASK);
+	if (i < op->data.nbytes) {
+		memcpy(&val, op->data.buf.out + i, op->data.nbytes - i);
+		val = fsl_qspi_endian_xchg(q, val);
+		qspi_writel(q, val, base + QUADSPI_TBDR);
 	}
 
-	qspi_write32(priv->flags, &regs->mcr, mcr_reg);
+	if (needs_fill_txfifo(q)) {
+		for (i = op->data.nbytes; i < 16; i += 4)
+			qspi_writel(q, 0, base + QUADSPI_TBDR);
+	}
 }
 
-static void qspi_op_write(struct fsl_qspi_priv *priv, u8 *txbuf, u32 len)
+static void fsl_qspi_read_rxfifo(struct fsl_qspi *q,
+				 const struct spi_mem_op *op)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 mcr_reg, data, reg, status_reg, seqid;
-	int i, size, tx_size;
-	u32 to_or_from = 0;
-
-	mcr_reg = qspi_read32(priv->flags, &regs->mcr);
-	qspi_write32(priv->flags, &regs->mcr,
-		     QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
-		     mcr_reg);
-	qspi_write32(priv->flags, &regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
-
-	status_reg = 0;
-	while ((status_reg & FLASH_STATUS_WEL) != FLASH_STATUS_WEL) {
-		WATCHDOG_RESET();
-
-		qspi_write32(priv->flags, &regs->ipcr,
-			     (SEQID_WREN << QSPI_IPCR_SEQID_SHIFT) | 0);
-		while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-			;
-
-		qspi_write32(priv->flags, &regs->ipcr,
-			     (SEQID_RDSR << QSPI_IPCR_SEQID_SHIFT) | 1);
-		while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-			;
+	void __iomem *base = q->iobase;
+	int i;
+	u8 *buf = op->data.buf.in;
+	u32 val;
 
-		reg = qspi_read32(priv->flags, &regs->rbsr);
-		if (reg & QSPI_RBSR_RDBFL_MASK) {
-			status_reg = qspi_read32(priv->flags, &regs->rbdr[0]);
-			status_reg = qspi_endian_xchg(priv, status_reg);
-		}
-		qspi_write32(priv->flags, &regs->mcr,
-			     qspi_read32(priv->flags, &regs->mcr) |
-			     QSPI_MCR_CLR_RXF_MASK);
+	for (i = 0; i < ALIGN_DOWN(op->data.nbytes, 4); i += 4) {
+		val = qspi_readl(q, base + QUADSPI_RBDR(i / 4));
+		val = fsl_qspi_endian_xchg(q, val);
+		memcpy(buf + i, &val, 4);
 	}
 
-	/* Default is page programming */
-	seqid = SEQID_PP;
-	if (priv->cur_seqid == QSPI_CMD_WRAR)
-		seqid = SEQID_WRAR;
-#ifdef CONFIG_SPI_FLASH_BAR
-	if (priv->cur_seqid == QSPI_CMD_BRWR)
-		seqid = SEQID_BRWR;
-	else if (priv->cur_seqid == QSPI_CMD_WREAR)
-		seqid = SEQID_WREAR;
-#endif
-
-	to_or_from = priv->sf_addr + priv->cur_amba_base;
-
-	qspi_write32(priv->flags, &regs->sfar, to_or_from);
-
-	tx_size = (len > priv->devtype_data->txfifo) ?
-		priv->devtype_data->txfifo : len;
-
-	size = tx_size / 16;
-	/*
-	 * There must be atleast 128bit data
-	 * available in TX FIFO for any pop operation
-	 */
-	if (tx_size % 16)
-		size++;
-	for (i = 0; i < size * 4; i++) {
-		memcpy(&data, txbuf, 4);
-		data = qspi_endian_xchg(priv, data);
-		qspi_write32(priv->flags, &regs->tbdr, data);
-		txbuf += 4;
+	if (i < op->data.nbytes) {
+		val = qspi_readl(q, base + QUADSPI_RBDR(i / 4));
+		val = fsl_qspi_endian_xchg(q, val);
+		memcpy(buf + i, &val, op->data.nbytes - i);
 	}
-
-	qspi_write32(priv->flags, &regs->ipcr,
-		     (seqid << QSPI_IPCR_SEQID_SHIFT) | tx_size);
-	while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-		;
-
-	qspi_write32(priv->flags, &regs->mcr, mcr_reg);
 }
 
-static void qspi_op_rdsr(struct fsl_qspi_priv *priv, void *rxbuf, u32 len)
+static int fsl_qspi_readl_poll_tout(struct fsl_qspi *q, void __iomem *base,
+				    u32 mask, u32 delay_us, u32 timeout_us)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 mcr_reg, reg, data;
-
-	mcr_reg = qspi_read32(priv->flags, &regs->mcr);
-	qspi_write32(priv->flags, &regs->mcr,
-		     QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
-		     mcr_reg);
-	qspi_write32(priv->flags, &regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
-
-	qspi_write32(priv->flags, &regs->sfar, priv->cur_amba_base);
-
-	qspi_write32(priv->flags, &regs->ipcr,
-		     (SEQID_RDSR << QSPI_IPCR_SEQID_SHIFT) | 0);
-	while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-		;
-
-	while (1) {
-		WATCHDOG_RESET();
+	u32 reg;
 
-		reg = qspi_read32(priv->flags, &regs->rbsr);
-		if (reg & QSPI_RBSR_RDBFL_MASK) {
-			data = qspi_read32(priv->flags, &regs->rbdr[0]);
-			data = qspi_endian_xchg(priv, data);
-			memcpy(rxbuf, &data, len);
-			qspi_write32(priv->flags, &regs->mcr,
-				     qspi_read32(priv->flags, &regs->mcr) |
-				     QSPI_MCR_CLR_RXF_MASK);
-			break;
-		}
-	}
+	if (!q->devtype_data->little_endian)
+		mask = (u32)cpu_to_be32(mask);
 
-	qspi_write32(priv->flags, &regs->mcr, mcr_reg);
+	return readl_poll_timeout(base, reg, !(reg & mask), timeout_us);
 }
 
-static void qspi_op_erase(struct fsl_qspi_priv *priv)
+static int fsl_qspi_do_op(struct fsl_qspi *q, const struct spi_mem_op *op)
 {
-	struct fsl_qspi_regs *regs = priv->regs;
-	u32 mcr_reg;
-	u32 to_or_from = 0;
+	void __iomem *base = q->iobase;
+	int err = 0;
 
-	mcr_reg = qspi_read32(priv->flags, &regs->mcr);
-	qspi_write32(priv->flags, &regs->mcr,
-		     QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
-		     mcr_reg);
-	qspi_write32(priv->flags, &regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
-
-	to_or_from = priv->sf_addr + priv->cur_amba_base;
-	qspi_write32(priv->flags, &regs->sfar, to_or_from);
+	/*
+	 * Always start the sequence at the same index since we update
+	 * the LUT at each exec_op() call. And also specify the DATA
+	 * length, since it's has not been specified in the LUT.
+	 */
+	qspi_writel(q, op->data.nbytes | QUADSPI_IPCR_SEQID(SEQID_LUT),
+		    base + QUADSPI_IPCR);
 
-	qspi_write32(priv->flags, &regs->ipcr,
-		     (SEQID_WREN << QSPI_IPCR_SEQID_SHIFT) | 0);
-	while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-		;
+	/* wait for the controller being ready */
+	err = fsl_qspi_readl_poll_tout(q, base + QUADSPI_SR,
+				       (QUADSPI_SR_IP_ACC_MASK |
+					QUADSPI_SR_AHB_ACC_MASK),
+					10, 1000);
 
-	if (priv->cur_seqid == QSPI_CMD_SE) {
-		qspi_write32(priv->flags, &regs->ipcr,
-			     (SEQID_SE << QSPI_IPCR_SEQID_SHIFT) | 0);
-	} else if (priv->cur_seqid == QSPI_CMD_BE_4K) {
-		qspi_write32(priv->flags, &regs->ipcr,
-			     (SEQID_BE_4K << QSPI_IPCR_SEQID_SHIFT) | 0);
-	}
-	while (qspi_read32(priv->flags, &regs->sr) & QSPI_SR_BUSY_MASK)
-		;
+	if (!err && op->data.nbytes && op->data.dir == SPI_MEM_DATA_IN)
+		fsl_qspi_read_rxfifo(q, op);
 
-	qspi_write32(priv->flags, &regs->mcr, mcr_reg);
+	return err;
 }
 
-int qspi_xfer(struct fsl_qspi_priv *priv, unsigned int bitlen,
-		const void *dout, void *din, unsigned long flags)
+static int fsl_qspi_exec_op(struct spi_slave *slave,
+			    const struct spi_mem_op *op)
 {
-	u32 bytes = DIV_ROUND_UP(bitlen, 8);
-	static u32 wr_sfaddr;
-	u32 txbuf;
+	struct fsl_qspi *q = dev_get_priv(slave->dev->parent);
+	void __iomem *base = q->iobase;
+	u32 addr_offset = 0;
+	int err = 0;
 
-	WATCHDOG_RESET();
+	/* wait for the controller being ready */
+	fsl_qspi_readl_poll_tout(q, base + QUADSPI_SR, (QUADSPI_SR_IP_ACC_MASK |
+				 QUADSPI_SR_AHB_ACC_MASK), 10, 1000);
 
-	if (dout) {
-		if (flags & SPI_XFER_BEGIN) {
-			priv->cur_seqid = *(u8 *)dout;
-			memcpy(&txbuf, dout, 4);
-		}
+	fsl_qspi_select_mem(q, slave);
 
-		if (flags == SPI_XFER_END) {
-			priv->sf_addr = wr_sfaddr;
-			qspi_op_write(priv, (u8 *)dout, bytes);
-			return 0;
-		}
+	if (needs_amba_base_offset(q))
+		addr_offset = q->memmap_phy;
 
-		if (priv->cur_seqid == QSPI_CMD_FAST_READ ||
-		    priv->cur_seqid == QSPI_CMD_RDAR) {
-			priv->sf_addr = swab32(txbuf) & OFFSET_BITS_MASK;
-		} else if ((priv->cur_seqid == QSPI_CMD_SE) ||
-			   (priv->cur_seqid == QSPI_CMD_BE_4K)) {
-			priv->sf_addr = swab32(txbuf) & OFFSET_BITS_MASK;
-			qspi_op_erase(priv);
-		} else if (priv->cur_seqid == QSPI_CMD_PP ||
-			   priv->cur_seqid == QSPI_CMD_WRAR) {
-			wr_sfaddr = swab32(txbuf) & OFFSET_BITS_MASK;
-		} else if ((priv->cur_seqid == QSPI_CMD_BRWR) ||
-			 (priv->cur_seqid == QSPI_CMD_WREAR)) {
-#ifdef CONFIG_SPI_FLASH_BAR
-			wr_sfaddr = 0;
-#endif
-		}
-	}
+	qspi_writel(q,
+		    q->selected * q->devtype_data->ahb_buf_size + addr_offset,
+		    base + QUADSPI_SFAR);
 
-	if (din) {
-		if (priv->cur_seqid == QSPI_CMD_FAST_READ) {
-#ifdef CONFIG_SYS_FSL_QSPI_AHB
-			qspi_ahb_read(priv, din, bytes);
-#else
-			qspi_op_read(priv, din, bytes);
-#endif
-		} else if (priv->cur_seqid == QSPI_CMD_RDAR) {
-			qspi_op_read(priv, din, bytes);
-		} else if (priv->cur_seqid == QSPI_CMD_RDID)
-			qspi_op_rdid(priv, din, bytes);
-		else if (priv->cur_seqid == QSPI_CMD_RDSR)
-			qspi_op_rdsr(priv, din, bytes);
-#ifdef CONFIG_SPI_FLASH_BAR
-		else if ((priv->cur_seqid == QSPI_CMD_BRRD) ||
-			 (priv->cur_seqid == QSPI_CMD_RDEAR)) {
-			priv->sf_addr = 0;
-			qspi_op_rdbank(priv, din, bytes);
-		}
-#endif
-	}
+	qspi_writel(q, qspi_readl(q, base + QUADSPI_MCR) |
+		    QUADSPI_MCR_CLR_RXF_MASK | QUADSPI_MCR_CLR_TXF_MASK,
+		    base + QUADSPI_MCR);
 
-#ifdef CONFIG_SYS_FSL_QSPI_AHB
-	if ((priv->cur_seqid == QSPI_CMD_SE) ||
-	    (priv->cur_seqid == QSPI_CMD_PP) ||
-	    (priv->cur_seqid == QSPI_CMD_BE_4K) ||
-	    (priv->cur_seqid == QSPI_CMD_WREAR) ||
-	    (priv->cur_seqid == QSPI_CMD_BRWR))
-		qspi_ahb_invalid(priv);
-#endif
+	qspi_writel(q, QUADSPI_SPTRCLR_BFPTRC | QUADSPI_SPTRCLR_IPPTRC,
+		    base + QUADSPI_SPTRCLR);
 
-	return 0;
-}
+	fsl_qspi_prepare_lut(q, op);
 
-void qspi_module_disable(struct fsl_qspi_priv *priv, u8 disable)
-{
-	u32 mcr_val;
+	/*
+	 * If we have large chunks of data, we read them through the AHB bus
+	 * by accessing the mapped memory. In all other cases we use
+	 * IP commands to access the flash.
+	 */
+	if (op->data.nbytes > (q->devtype_data->rxfifo - 4) &&
+	    op->data.dir == SPI_MEM_DATA_IN) {
+		fsl_qspi_read_ahb(q, op);
+	} else {
+		qspi_writel(q, QUADSPI_RBCT_WMRK_MASK |
+			    QUADSPI_RBCT_RXBRD_USEIPS, base + QUADSPI_RBCT);
 
-	mcr_val = qspi_read32(priv->flags, &priv->regs->mcr);
-	if (disable)
-		mcr_val |= QSPI_MCR_MDIS_MASK;
-	else
-		mcr_val &= ~QSPI_MCR_MDIS_MASK;
-	qspi_write32(priv->flags, &priv->regs->mcr, mcr_val);
-}
+		if (op->data.nbytes && op->data.dir == SPI_MEM_DATA_OUT)
+			fsl_qspi_fill_txfifo(q, op);
 
-void qspi_cfg_smpr(struct fsl_qspi_priv *priv, u32 clear_bits, u32 set_bits)
-{
-	u32 smpr_val;
+		err = fsl_qspi_do_op(q, op);
+	}
+
+	/* Invalidate the data in the AHB buffer. */
+	fsl_qspi_invalidate(q);
 
-	smpr_val = qspi_read32(priv->flags, &priv->regs->smpr);
-	smpr_val &= ~clear_bits;
-	smpr_val |= set_bits;
-	qspi_write32(priv->flags, &priv->regs->smpr, smpr_val);
+	return err;
 }
 
-static int fsl_qspi_child_pre_probe(struct udevice *dev)
+static int fsl_qspi_adjust_op_size(struct spi_slave *slave,
+				   struct spi_mem_op *op)
 {
-	struct spi_slave *slave = dev_get_parent_priv(dev);
-	struct fsl_qspi_priv *priv = dev_get_priv(dev_get_parent(dev));
+	struct fsl_qspi *q = dev_get_priv(slave->dev->parent);
 
-	slave->max_write_size = priv->devtype_data->txfifo;
+	if (op->data.dir == SPI_MEM_DATA_OUT) {
+		if (op->data.nbytes > q->devtype_data->txfifo)
+			op->data.nbytes = q->devtype_data->txfifo;
+	} else {
+		if (op->data.nbytes > q->devtype_data->ahb_buf_size)
+			op->data.nbytes = q->devtype_data->ahb_buf_size;
+		else if (op->data.nbytes > (q->devtype_data->rxfifo - 4))
+			op->data.nbytes = ALIGN_DOWN(op->data.nbytes, 8);
+	}
 
 	return 0;
 }
 
-static int fsl_qspi_probe(struct udevice *bus)
+static int fsl_qspi_default_setup(struct fsl_qspi *q)
 {
-	u32 amba_size_per_chip;
-	struct fsl_qspi_platdata *plat = dev_get_platdata(bus);
-	struct fsl_qspi_priv *priv = dev_get_priv(bus);
-	struct dm_spi_bus *dm_spi_bus;
-	int i, ret;
+	void __iomem *base = q->iobase;
+	u32 reg, addr_offset = 0;
 
-	dm_spi_bus = bus->uclass_priv;
-
-	dm_spi_bus->max_hz = plat->speed_hz;
+	/* Reset the module */
+	qspi_writel(q, QUADSPI_MCR_SWRSTSD_MASK | QUADSPI_MCR_SWRSTHD_MASK,
+		    base + QUADSPI_MCR);
+	udelay(1);
 
-	priv->regs = (struct fsl_qspi_regs *)(uintptr_t)plat->reg_base;
-	priv->flags = plat->flags;
+	/* Disable the module */
+	qspi_writel(q, QUADSPI_MCR_MDIS_MASK | QUADSPI_MCR_RESERVED_MASK,
+		    base + QUADSPI_MCR);
 
-	priv->speed_hz = plat->speed_hz;
 	/*
-	 * QSPI SFADR width is 32bits, the max dest addr is 4GB-1.
-	 * AMBA memory zone should be located on the 0~4GB space
-	 * even on a 64bits cpu.
+	 * Previous boot stages (BootROM, bootloader) might have used DDR
+	 * mode and did not clear the TDH bits. As we currently use SDR mode
+	 * only, clear the TDH bits if necessary.
 	 */
-	priv->amba_base[0] = (u32)plat->amba_base;
-	priv->amba_total_size = (u32)plat->amba_total_size;
-	priv->flash_num = plat->flash_num;
-	priv->num_chipselect = plat->num_chipselect;
+	if (needs_tdh_setting(q))
+		qspi_writel(q, qspi_readl(q, base + QUADSPI_FLSHCR) &
+			    ~QUADSPI_FLSHCR_TDH_MASK,
+			    base + QUADSPI_FLSHCR);
 
-	priv->devtype_data = (struct fsl_qspi_devtype_data *)dev_get_driver_data(bus);
-	if (!priv->devtype_data) {
-		printf("ERROR : No devtype_data found\n");
-		return -ENODEV;
-	}
-
-	debug("devtype=%d, txfifo=%d, rxfifo=%d, ahb=%d, data=0x%x\n",
-		priv->devtype_data->devtype,
-		priv->devtype_data->txfifo,
-		priv->devtype_data->rxfifo,
-		priv->devtype_data->ahb_buf_size,
-		priv->devtype_data->driver_data);
+	reg = qspi_readl(q, base + QUADSPI_SMPR);
+	qspi_writel(q, reg & ~(QUADSPI_SMPR_FSDLY_MASK
+			| QUADSPI_SMPR_FSPHS_MASK
+			| QUADSPI_SMPR_HSENA_MASK
+			| QUADSPI_SMPR_DDRSMP_MASK), base + QUADSPI_SMPR);
 
-	/* make sure controller is not busy anywhere */
-	ret = is_controller_busy(priv);
+	/* We only use the buffer3 for AHB read */
+	qspi_writel(q, 0, base + QUADSPI_BUF0IND);
+	qspi_writel(q, 0, base + QUADSPI_BUF1IND);
+	qspi_writel(q, 0, base + QUADSPI_BUF2IND);
 
-	if (ret) {
-		debug("ERROR : The controller is busy\n");
-		return ret;
-	}
+	qspi_writel(q, QUADSPI_BFGENCR_SEQID(SEQID_LUT),
+		    q->iobase + QUADSPI_BFGENCR);
+	qspi_writel(q, QUADSPI_RBCT_WMRK_MASK, base + QUADSPI_RBCT);
+	qspi_writel(q, QUADSPI_BUF3CR_ALLMST_MASK |
+		    QUADSPI_BUF3CR_ADATSZ(q->devtype_data->ahb_buf_size / 8),
+		    base + QUADSPI_BUF3CR);
 
-	qspi_write32(priv->flags, &priv->regs->mcr,
-		     QSPI_MCR_RESERVED_MASK | QSPI_MCR_MDIS_MASK |
-		     QSPI_MCR_END_CFD_LE);
-
-	qspi_cfg_smpr(priv, ~(QSPI_SMPR_FSDLY_MASK | QSPI_SMPR_DDRSMP_MASK |
-		QSPI_SMPR_FSPHS_MASK | QSPI_SMPR_HSENA_MASK), 0);
+	if (needs_amba_base_offset(q))
+		addr_offset = q->memmap_phy;
 
 	/*
-	 * Assign AMBA memory zone for every chipselect
-	 * QuadSPI has two channels, every channel has two chipselects.
-	 * If the property 'num-cs' in dts is 2, the AMBA memory will be divided
-	 * into two parts and assign to every channel. This indicate that every
-	 * channel only has one valid chipselect.
-	 * If the property 'num-cs' in dts is 4, the AMBA memory will be divided
-	 * into four parts and assign to every chipselect.
-	 * Every channel will has two valid chipselects.
+	 * In HW there can be a maximum of four chips on two buses with
+	 * two chip selects on each bus. We use four chip selects in SW
+	 * to differentiate between the four chips.
+	 * We use ahb_buf_size for each chip and set SFA1AD, SFA2AD, SFB1AD,
+	 * SFB2AD accordingly.
 	 */
-	amba_size_per_chip = priv->amba_total_size >>
-			     (priv->num_chipselect >> 1);
-	for (i = 1 ; i < priv->num_chipselect ; i++)
-		priv->amba_base[i] =
-			amba_size_per_chip + priv->amba_base[i - 1];
-
-	/*
-	 * Any read access to non-implemented addresses will provide
-	 * undefined results.
-	 *
-	 * In case single die flash devices, TOP_ADDR_MEMA2 and
-	 * TOP_ADDR_MEMB2 should be initialized/programmed to
-	 * TOP_ADDR_MEMA1 and TOP_ADDR_MEMB1 respectively - in effect,
-	 * setting the size of these devices to 0.  This would ensure
-	 * that the complete memory map is assigned to only one flash device.
-	 */
-	qspi_write32(priv->flags, &priv->regs->sfa1ad,
-		     priv->amba_base[0] + amba_size_per_chip);
-	switch (priv->num_chipselect) {
-	case 1:
-		break;
-	case 2:
-		qspi_write32(priv->flags, &priv->regs->sfa2ad,
-			     priv->amba_base[1]);
-		qspi_write32(priv->flags, &priv->regs->sfb1ad,
-			     priv->amba_base[1] + amba_size_per_chip);
-		qspi_write32(priv->flags, &priv->regs->sfb2ad,
-			     priv->amba_base[1] + amba_size_per_chip);
-		break;
-	case 4:
-		qspi_write32(priv->flags, &priv->regs->sfa2ad,
-			     priv->amba_base[2]);
-		qspi_write32(priv->flags, &priv->regs->sfb1ad,
-			     priv->amba_base[3]);
-		qspi_write32(priv->flags, &priv->regs->sfb2ad,
-			     priv->amba_base[3] + amba_size_per_chip);
-		break;
-	default:
-		debug("Error: Unsupported chipselect number %u!\n",
-		      priv->num_chipselect);
-		qspi_module_disable(priv, 1);
-		return -EINVAL;
-	}
-
-	qspi_set_lut(priv);
+	qspi_writel(q, q->devtype_data->ahb_buf_size + addr_offset,
+		    base + QUADSPI_SFA1AD);
+	qspi_writel(q, q->devtype_data->ahb_buf_size * 2 + addr_offset,
+		    base + QUADSPI_SFA2AD);
+	qspi_writel(q, q->devtype_data->ahb_buf_size * 3 + addr_offset,
+		    base + QUADSPI_SFB1AD);
+	qspi_writel(q, q->devtype_data->ahb_buf_size * 4 + addr_offset,
+		    base + QUADSPI_SFB2AD);
 
-#ifdef CONFIG_SYS_FSL_QSPI_AHB
-	qspi_init_ahb_read(priv);
-#endif
+	q->selected = -1;
 
-	qspi_module_disable(priv, 0);
-
+	/* Enable the module */
+	qspi_writel(q, QUADSPI_MCR_RESERVED_MASK | QUADSPI_MCR_END_CFG_MASK,
+		    base + QUADSPI_MCR);
 	return 0;
 }
 
+static const struct spi_controller_mem_ops fsl_qspi_mem_ops = {
+	.adjust_op_size = fsl_qspi_adjust_op_size,
+	.supports_op = fsl_qspi_supports_op,
+	.exec_op = fsl_qspi_exec_op,
+};
+
-static int fsl_qspi_ofdata_to_platdata(struct udevice *bus)
+static int fsl_qspi_probe(struct udevice *bus)
 {
-	struct fdt_resource res_regs, res_mem;
-	struct fsl_qspi_platdata *plat = bus->platdata;
+	struct dm_spi_bus *dm_bus = bus->uclass_priv;
+	struct fsl_qspi *q = dev_get_priv(bus);
 	const void *blob = gd->fdt_blob;
 	int node = dev_of_offset(bus);
-	int ret, flash_num = 0, subnode;
+	struct fdt_resource res;
+	int ret;
 
-	if (fdtdec_get_bool(blob, node, "big-endian"))
-		plat->flags |= QSPI_FLAG_REGMAP_ENDIAN_BIG;
+	q->dev = bus;
+	q->devtype_data = (struct fsl_qspi_devtype_data *)
+			   dev_get_driver_data(bus);
 
-	ret = fdt_get_named_resource(blob, node, "reg", "reg-names",
-				     "QuadSPI", &res_regs);
+	/* find the resources */
+	ret = fdt_get_named_resource(blob, node, "reg", "reg-names", "QuadSPI",
+				     &res);
 	if (ret) {
-		debug("Error: can't get regs base addresses(ret = %d)!\n", ret);
+		dev_err(bus, "Can't get regs base addresses(ret = %d)!\n", ret);
 		return -ENOMEM;
 	}
+
+	q->iobase = map_physmem(res.start, res.end - res.start, MAP_NOCACHE);
+
 	ret = fdt_get_named_resource(blob, node, "reg", "reg-names",
-				     "QuadSPI-memory", &res_mem);
+				     "QuadSPI-memory", &res);
 	if (ret) {
-		debug("Error: can't get AMBA base addresses(ret = %d)!\n", ret);
+		dev_err(bus, "Can't get AMBA base addresses(ret = %d)!\n", ret);
 		return -ENOMEM;
 	}
 
-	/* Count flash numbers */
-	fdt_for_each_subnode(subnode, blob, node)
-		++flash_num;
-
-	if (flash_num == 0) {
-		debug("Error: Missing flashes!\n");
-		return -ENODEV;
-	}
-
-	plat->speed_hz = fdtdec_get_int(blob, node, "spi-max-frequency",
-					FSL_QSPI_DEFAULT_SCK_FREQ);
-	plat->num_chipselect = fdtdec_get_int(blob, node, "num-cs",
-					      FSL_QSPI_MAX_CHIPSELECT_NUM);
+	q->ahb_addr = map_physmem(res.start, res.end - res.start, MAP_NOCACHE);
+	q->memmap_phy = res.start;
 
-	plat->reg_base = res_regs.start;
-	plat->amba_base = res_mem.start;
-	plat->amba_total_size = res_mem.end - res_mem.start + 1;
-	plat->flash_num = flash_num;
+	dm_bus->max_hz = fdtdec_get_int(blob, node, "spi-max-frequency",
+					66000000);
 
-	debug("%s: regs=<0x%llx> <0x%llx, 0x%llx>, max-frequency=%d, endianess=%s\n",
-	      __func__,
-	      (u64)plat->reg_base,
-	      (u64)plat->amba_base,
-	      (u64)plat->amba_total_size,
-	      plat->speed_hz,
-	      plat->flags & QSPI_FLAG_REGMAP_ENDIAN_BIG ? "be" : "le"
-	      );
+	fsl_qspi_default_setup(q);
 
 	return 0;
 }
 
 static int fsl_qspi_xfer(struct udevice *dev, unsigned int bitlen,
-		const void *dout, void *din, unsigned long flags)
+			 const void *dout, void *din, unsigned long flags)
 {
-	struct fsl_qspi_priv *priv;
-	struct udevice *bus;
-
-	bus = dev->parent;
-	priv = dev_get_priv(bus);
-
-	return qspi_xfer(priv, bitlen, dout, din, flags);
+	return 0;
 }
 
 static int fsl_qspi_claim_bus(struct udevice *dev)
 {
-	struct fsl_qspi_priv *priv;
-	struct udevice *bus;
-	struct dm_spi_slave_platdata *slave_plat = dev_get_parent_platdata(dev);
-	int ret;
-
-	bus = dev->parent;
-	priv = dev_get_priv(bus);
-
-	/* make sure controller is not busy anywhere */
-	ret = is_controller_busy(priv);
-
-	if (ret) {
-		debug("ERROR : The controller is busy\n");
-		return ret;
-	}
-
-	priv->cur_amba_base = priv->amba_base[slave_plat->cs];
-
-	qspi_module_disable(priv, 0);
-
 	return 0;
 }
 
 static int fsl_qspi_release_bus(struct udevice *dev)
 {
-	struct fsl_qspi_priv *priv;
-	struct udevice *bus;
-
-	bus = dev->parent;
-	priv = dev_get_priv(bus);
-
-	qspi_module_disable(priv, 1);
-
 	return 0;
 }
 
 static int fsl_qspi_set_speed(struct udevice *bus, uint speed)
 {
-	/* Nothing to do */
 	return 0;
 }
 
 static int fsl_qspi_set_mode(struct udevice *bus, uint mode)
 {
-	/* Nothing to do */
 	return 0;
 }
 
@@ -1146,14 +785,17 @@
 	.xfer		= fsl_qspi_xfer,
 	.set_speed	= fsl_qspi_set_speed,
 	.set_mode	= fsl_qspi_set_mode,
+	.mem_ops	= &fsl_qspi_mem_ops,
 };
 
 static const struct udevice_id fsl_qspi_ids[] = {
-	{ .compatible = "fsl,vf610-qspi", .data = (ulong)&vybrid_data },
-	{ .compatible = "fsl,imx6sx-qspi", .data = (ulong)&imx6sx_data },
-	{ .compatible = "fsl,imx6ul-qspi", .data = (ulong)&imx6ul_7d_data },
-	{ .compatible = "fsl,imx7d-qspi", .data = (ulong)&imx6ul_7d_data },
-	{ .compatible = "fsl,imx7ulp-qspi", .data = (ulong)&imx7ulp_data },
+	{ .compatible = "fsl,vf610-qspi", .data = (ulong)&vybrid_data, },
+	{ .compatible = "fsl,imx6sx-qspi", .data = (ulong)&imx6sx_data, },
+	{ .compatible = "fsl,imx6ul-qspi", .data = (ulong)&imx6ul_data, },
+	{ .compatible = "fsl,imx7d-qspi", .data = (ulong)&imx7d_data, },
+	{ .compatible = "fsl,ls1021a-qspi", .data = (ulong)&ls1021a_data, },
+	{ .compatible = "fsl,ls1088a-qspi", .data = (ulong)&ls1088a_data, },
+	{ .compatible = "fsl,ls2080a-qspi", .data = (ulong)&ls2080a_data, },
 	{ }
 };
 
@@ -1162,9 +804,6 @@
 	.id	= UCLASS_SPI,
 	.of_match = fsl_qspi_ids,
 	.ops	= &fsl_qspi_ops,
-	.ofdata_to_platdata = fsl_qspi_ofdata_to_platdata,
-	.platdata_auto_alloc_size = sizeof(struct fsl_qspi_platdata),
-	.priv_auto_alloc_size = sizeof(struct fsl_qspi_priv),
+	.priv_auto_alloc_size = sizeof(struct fsl_qspi),
 	.probe	= fsl_qspi_probe,
-	.child_pre_probe = fsl_qspi_child_pre_probe,
 };
diff --git a/drivers/spi/fsl_qspi.h b/drivers/spi/fsl_qspi.h
deleted file mode 100644
index 9e61a85..0000000
--- a/drivers/spi/fsl_qspi.h
+++ /dev/null
@@ -1,145 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-/*
- * Copyright 2013-2014 Freescale Semiconductor, Inc.
- *
- * Register definitions for Freescale QSPI
- */
-
-#ifndef _FSL_QSPI_H_
-#define _FSL_QSPI_H_
-
-struct fsl_qspi_regs {
-	u32 mcr;
-	u32 rsvd0[1];
-	u32 ipcr;
-	u32 flshcr;
-	u32 buf0cr;
-	u32 buf1cr;
-	u32 buf2cr;
-	u32 buf3cr;
-	u32 bfgencr;
-	u32 soccr;
-	u32 rsvd1[2];
-	u32 buf0ind;
-	u32 buf1ind;
-	u32 buf2ind;
-	u32 rsvd2[49];
-	u32 sfar;
-	u32 rsvd3[1];
-	u32 smpr;
-	u32 rbsr;
-	u32 rbct;
-	u32 rsvd4[15];
-	u32 tbsr;
-	u32 tbdr;
-	u32 rsvd5[1];
-	u32 sr;
-	u32 fr;
-	u32 rser;
-	u32 spndst;
-	u32 sptrclr;
-	u32 rsvd6[4];
-	u32 sfa1ad;
-	u32 sfa2ad;
-	u32 sfb1ad;
-	u32 sfb2ad;
-	u32 rsvd7[28];
-	u32 rbdr[32];
-	u32 rsvd8[32];
-	u32 lutkey;
-	u32 lckcr;
-	u32 rsvd9[2];
-	u32 lut[64];
-};
-
-#define QSPI_IPCR_SEQID_SHIFT		24
-#define QSPI_IPCR_SEQID_MASK		(0xf << QSPI_IPCR_SEQID_SHIFT)
-
-#define QSPI_MCR_END_CFD_SHIFT		2
-#define QSPI_MCR_END_CFD_MASK		(3 << QSPI_MCR_END_CFD_SHIFT)
-#ifdef CONFIG_SYS_FSL_QSPI_AHB
-/* AHB needs 64bit operation */
-#define QSPI_MCR_END_CFD_LE		(3 << QSPI_MCR_END_CFD_SHIFT)
-#else
-#define QSPI_MCR_END_CFD_LE		(1 << QSPI_MCR_END_CFD_SHIFT)
-#endif
-#define QSPI_MCR_DDR_EN_SHIFT		7
-#define QSPI_MCR_DDR_EN_MASK		(1 << QSPI_MCR_DDR_EN_SHIFT)
-#define QSPI_MCR_CLR_RXF_SHIFT		10
-#define QSPI_MCR_CLR_RXF_MASK		(1 << QSPI_MCR_CLR_RXF_SHIFT)
-#define QSPI_MCR_CLR_TXF_SHIFT		11
-#define QSPI_MCR_CLR_TXF_MASK		(1 << QSPI_MCR_CLR_TXF_SHIFT)
-#define QSPI_MCR_MDIS_SHIFT		14
-#define QSPI_MCR_MDIS_MASK		(1 << QSPI_MCR_MDIS_SHIFT)
-#define QSPI_MCR_RESERVED_SHIFT		16
-#define QSPI_MCR_RESERVED_MASK		(0xf << QSPI_MCR_RESERVED_SHIFT)
-#define QSPI_MCR_SWRSTHD_SHIFT		1
-#define QSPI_MCR_SWRSTHD_MASK		(1 << QSPI_MCR_SWRSTHD_SHIFT)
-#define QSPI_MCR_SWRSTSD_SHIFT		0
-#define QSPI_MCR_SWRSTSD_MASK		(1 << QSPI_MCR_SWRSTSD_SHIFT)
-
-#define QSPI_SMPR_HSENA_SHIFT		0
-#define QSPI_SMPR_HSENA_MASK		(1 << QSPI_SMPR_HSENA_SHIFT)
-#define QSPI_SMPR_FSPHS_SHIFT		5
-#define QSPI_SMPR_FSPHS_MASK		(1 << QSPI_SMPR_FSPHS_SHIFT)
-#define QSPI_SMPR_FSDLY_SHIFT		6
-#define QSPI_SMPR_FSDLY_MASK		(1 << QSPI_SMPR_FSDLY_SHIFT)
-#define QSPI_SMPR_DDRSMP_SHIFT		16
-#define QSPI_SMPR_DDRSMP_MASK		(7 << QSPI_SMPR_DDRSMP_SHIFT)
-
-#define QSPI_BUFXCR_INVALID_MSTRID	0xe
-#define QSPI_BUF3CR_ALLMST_SHIFT	31
-#define QSPI_BUF3CR_ALLMST_MASK		(1 << QSPI_BUF3CR_ALLMST_SHIFT)
-#define QSPI_BUF3CR_ADATSZ_SHIFT	8
-#define QSPI_BUF3CR_ADATSZ_MASK		(0xFF << QSPI_BUF3CR_ADATSZ_SHIFT)
-
-#define QSPI_BFGENCR_SEQID_SHIFT	12
-#define QSPI_BFGENCR_SEQID_MASK		(0xf << QSPI_BFGENCR_SEQID_SHIFT)
-#define QSPI_BFGENCR_PAR_EN_SHIFT	16
-#define QSPI_BFGENCR_PAR_EN_MASK	(1 << QSPI_BFGENCR_PAR_EN_SHIFT)
-
-#define QSPI_RBSR_RDBFL_SHIFT		8
-#define QSPI_RBSR_RDBFL_MASK		(0x3f << QSPI_RBSR_RDBFL_SHIFT)
-
-#define QSPI_RBCT_RXBRD_SHIFT		8
-#define QSPI_RBCT_RXBRD_USEIPS		(1 << QSPI_RBCT_RXBRD_SHIFT)
-
-#define QSPI_SR_AHB_ACC_SHIFT		2
-#define QSPI_SR_AHB_ACC_MASK		(1 << QSPI_SR_AHB_ACC_SHIFT)
-#define QSPI_SR_IP_ACC_SHIFT		1
-#define QSPI_SR_IP_ACC_MASK		(1 << QSPI_SR_IP_ACC_SHIFT)
-#define QSPI_SR_BUSY_SHIFT		0
-#define QSPI_SR_BUSY_MASK		(1 << QSPI_SR_BUSY_SHIFT)
-
-#define QSPI_LCKCR_LOCK			0x1
-#define QSPI_LCKCR_UNLOCK		0x2
-
-#define LUT_KEY_VALUE			0x5af05af0
-
-#define OPRND0_SHIFT			0
-#define OPRND0(x)			((x) << OPRND0_SHIFT)
-#define PAD0_SHIFT			8
-#define PAD0(x)				((x) << PAD0_SHIFT)
-#define INSTR0_SHIFT			10
-#define INSTR0(x)			((x) << INSTR0_SHIFT)
-#define OPRND1_SHIFT			16
-#define OPRND1(x)			((x) << OPRND1_SHIFT)
-#define PAD1_SHIFT			24
-#define PAD1(x)				((x) << PAD1_SHIFT)
-#define INSTR1_SHIFT			26
-#define INSTR1(x)			((x) << INSTR1_SHIFT)
-
-#define LUT_CMD				1
-#define LUT_ADDR			2
-#define LUT_DUMMY			3
-#define LUT_READ			7
-#define LUT_WRITE			8
-
-#define LUT_PAD1			0
-#define LUT_PAD2			1
-#define LUT_PAD4			2
-
-#define ADDR24BIT			0x18
-#define ADDR32BIT			0x20
-
-#endif /* _FSL_QSPI_H_ */
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index e900c99..ffbe20c 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -153,7 +153,7 @@
 	    spi_check_buswidth_req(slave, op->dummy.buswidth, true))
 		return false;
 
-	if (op->data.nbytes &&
+	if (op->data.dir != SPI_MEM_NO_DATA &&
 	    spi_check_buswidth_req(slave, op->data.buswidth,
 				   op->data.dir == SPI_MEM_DATA_OUT))
 		return false;
diff --git a/drivers/spi/spi-sifive.c b/drivers/spi/spi-sifive.c
index 969bd4b..4cab039 100644
--- a/drivers/spi/spi-sifive.c
+++ b/drivers/spi/spi-sifive.c
@@ -8,8 +8,10 @@
 
 #include <common.h>
 #include <dm.h>
+#include <dm/device_compat.h>
 #include <malloc.h>
-#include <spi.h>
+#include <spi-mem.h>
+#include <wait_bit.h>
 #include <asm/io.h>
 #include <linux/log2.h>
 #include <clk.h>
@@ -85,6 +87,11 @@
 #define SIFIVE_SPI_IP_TXWM               BIT(0)
 #define SIFIVE_SPI_IP_RXWM               BIT(1)
 
+/* format protocol */
+#define SIFIVE_SPI_PROTO_QUAD		4 /* 4 lines I/O protocol transfer */
+#define SIFIVE_SPI_PROTO_DUAL		2 /* 2 lines I/O protocol transfer */
+#define SIFIVE_SPI_PROTO_SINGLE		1 /* 1 line I/O protocol transfer */
+
 struct sifive_spi {
 	void		*regs;		/* base address of the registers */
 	u32		fifo_depth;
@@ -92,28 +99,29 @@
 	u32		cs_inactive;	/* Level of the CS pins when inactive*/
 	u32		freq;
 	u32		num_cs;
+	u8		fmt_proto;
 };
 
 static void sifive_spi_prep_device(struct sifive_spi *spi,
-				   struct dm_spi_slave_platdata *slave)
+				   struct dm_spi_slave_platdata *slave_plat)
 {
 	/* Update the chip select polarity */
-	if (slave->mode & SPI_CS_HIGH)
-		spi->cs_inactive &= ~BIT(slave->cs);
+	if (slave_plat->mode & SPI_CS_HIGH)
+		spi->cs_inactive &= ~BIT(slave_plat->cs);
 	else
-		spi->cs_inactive |= BIT(slave->cs);
+		spi->cs_inactive |= BIT(slave_plat->cs);
 	writel(spi->cs_inactive, spi->regs + SIFIVE_SPI_REG_CSDEF);
 
 	/* Select the correct device */
-	writel(slave->cs, spi->regs + SIFIVE_SPI_REG_CSID);
+	writel(slave_plat->cs, spi->regs + SIFIVE_SPI_REG_CSID);
 }
 
 static int sifive_spi_set_cs(struct sifive_spi *spi,
-			     struct dm_spi_slave_platdata *slave)
+			     struct dm_spi_slave_platdata *slave_plat)
 {
 	u32 cs_mode = SIFIVE_SPI_CSMODE_MODE_HOLD;
 
-	if (slave->mode & SPI_CS_HIGH)
+	if (slave_plat->mode & SPI_CS_HIGH)
 		cs_mode = SIFIVE_SPI_CSMODE_MODE_AUTO;
 
 	writel(cs_mode, spi->regs + SIFIVE_SPI_REG_CSMODE);
@@ -127,8 +135,8 @@
 }
 
 static void sifive_spi_prep_transfer(struct sifive_spi *spi,
-				     bool is_rx_xfer,
-				     struct dm_spi_slave_platdata *slave)
+				     struct dm_spi_slave_platdata *slave_plat,
+				     u8 *rx_ptr)
 {
 	u32 cr;
 
@@ -141,21 +149,26 @@
 
 	/* LSB first? */
 	cr &= ~SIFIVE_SPI_FMT_ENDIAN;
-	if (slave->mode & SPI_LSB_FIRST)
+	if (slave_plat->mode & SPI_LSB_FIRST)
 		cr |= SIFIVE_SPI_FMT_ENDIAN;
 
 	/* Number of wires ? */
 	cr &= ~SIFIVE_SPI_FMT_PROTO_MASK;
-	if ((slave->mode & SPI_TX_QUAD) || (slave->mode & SPI_RX_QUAD))
+	switch (spi->fmt_proto) {
+	case SIFIVE_SPI_PROTO_QUAD:
 		cr |= SIFIVE_SPI_FMT_PROTO_QUAD;
-	else if ((slave->mode & SPI_TX_DUAL) || (slave->mode & SPI_RX_DUAL))
+		break;
+	case SIFIVE_SPI_PROTO_DUAL:
 		cr |= SIFIVE_SPI_FMT_PROTO_DUAL;
-	else
+		break;
+	default:
 		cr |= SIFIVE_SPI_FMT_PROTO_SINGLE;
+		break;
+	}
 
 	/* SPI direction in/out ? */
 	cr &= ~SIFIVE_SPI_FMT_DIR;
-	if (!is_rx_xfer)
+	if (!rx_ptr)
 		cr |= SIFIVE_SPI_FMT_DIR;
 
 	writel(cr, spi->regs + SIFIVE_SPI_REG_FMT);
@@ -186,50 +199,62 @@
 	writel(tx_data, spi->regs + SIFIVE_SPI_REG_TXDATA);
 }
 
+static int sifive_spi_wait(struct sifive_spi *spi, u32 bit)
+{
+	return wait_for_bit_le32(spi->regs + SIFIVE_SPI_REG_IP,
+				 bit, true, 100, false);
+}
+
 static int sifive_spi_xfer(struct udevice *dev, unsigned int bitlen,
 			   const void *dout, void *din, unsigned long flags)
 {
 	struct udevice *bus = dev->parent;
 	struct sifive_spi *spi = dev_get_priv(bus);
-	struct dm_spi_slave_platdata *slave = dev_get_parent_platdata(dev);
-	const unsigned char *tx_ptr = dout;
+	struct dm_spi_slave_platdata *slave_plat = dev_get_parent_platdata(dev);
+	const u8 *tx_ptr = dout;
 	u8 *rx_ptr = din;
 	u32 remaining_len;
 	int ret;
 
 	if (flags & SPI_XFER_BEGIN) {
-		sifive_spi_prep_device(spi, slave);
+		sifive_spi_prep_device(spi, slave_plat);
 
-		ret = sifive_spi_set_cs(spi, slave);
+		ret = sifive_spi_set_cs(spi, slave_plat);
 		if (ret)
 			return ret;
 	}
 
-	sifive_spi_prep_transfer(spi, true, slave);
+	sifive_spi_prep_transfer(spi, slave_plat, rx_ptr);
 
 	remaining_len = bitlen / 8;
 
 	while (remaining_len) {
-		int n_words, tx_words, rx_words;
-
-		n_words = min(remaining_len, spi->fifo_depth);
+		unsigned int n_words = min(remaining_len, spi->fifo_depth);
+		unsigned int tx_words, rx_words;
 
 		/* Enqueue n_words for transmission */
-		if (tx_ptr) {
-			for (tx_words = 0; tx_words < n_words; ++tx_words) {
-				sifive_spi_tx(spi, tx_ptr);
-				sifive_spi_rx(spi, NULL);
-				tx_ptr++;
-			}
+		for (tx_words = 0; tx_words < n_words; tx_words++) {
+			if (!tx_ptr)
+				sifive_spi_tx(spi, NULL);
+			else
+				sifive_spi_tx(spi, tx_ptr++);
 		}
 
-		/* Read out all the data from the RX FIFO */
 		if (rx_ptr) {
-			for (rx_words = 0; rx_words < n_words; ++rx_words) {
-				sifive_spi_tx(spi, NULL);
-				sifive_spi_rx(spi, rx_ptr);
-				rx_ptr++;
-			}
+			/* Wait for transmission + reception to complete */
+			writel(n_words - 1, spi->regs + SIFIVE_SPI_REG_RXMARK);
+			ret = sifive_spi_wait(spi, SIFIVE_SPI_IP_RXWM);
+			if (ret)
+				return ret;
+
+			/* Read out all the data from the RX FIFO */
+			for (rx_words = 0; rx_words < n_words; rx_words++)
+				sifive_spi_rx(spi, rx_ptr++);
+		} else {
+			/* Wait for transmission to complete */
+			ret = sifive_spi_wait(spi, SIFIVE_SPI_IP_TXWM);
+			if (ret)
+				return ret;
 		}
 
 		remaining_len -= n_words;
@@ -241,6 +266,80 @@
 	return 0;
 }
 
+static int sifive_spi_exec_op(struct spi_slave *slave,
+			      const struct spi_mem_op *op)
+{
+	struct udevice *dev = slave->dev;
+	struct sifive_spi *spi = dev_get_priv(dev->parent);
+	unsigned long flags = SPI_XFER_BEGIN;
+	u8 opcode = op->cmd.opcode;
+	unsigned int pos = 0;
+	const void *tx_buf = NULL;
+	void *rx_buf = NULL;
+	int op_len, i;
+	int ret;
+
+	if (!op->addr.nbytes && !op->dummy.nbytes && !op->data.nbytes)
+		flags |= SPI_XFER_END;
+
+	spi->fmt_proto = op->cmd.buswidth;
+
+	/* send the opcode */
+	ret = sifive_spi_xfer(dev, 8, (void *)&opcode, NULL, flags);
+	if (ret < 0) {
+		dev_err(dev, "failed to xfer opcode\n");
+		return ret;
+	}
+
+	op_len = op->addr.nbytes + op->dummy.nbytes;
+	u8 op_buf[op_len];
+
+	/* send the addr + dummy */
+	if (op->addr.nbytes) {
+		/* fill address */
+		for (i = 0; i < op->addr.nbytes; i++)
+			op_buf[pos + i] = op->addr.val >>
+				(8 * (op->addr.nbytes - i - 1));
+
+		pos += op->addr.nbytes;
+
+		/* fill dummy */
+		if (op->dummy.nbytes)
+			memset(op_buf + pos, 0xff, op->dummy.nbytes);
+
+		/* make sure to set end flag, if no data bytes */
+		if (!op->data.nbytes)
+			flags |= SPI_XFER_END;
+
+		spi->fmt_proto = op->addr.buswidth;
+
+		ret = sifive_spi_xfer(dev, op_len * 8, op_buf, NULL, flags);
+		if (ret < 0) {
+			dev_err(dev, "failed to xfer addr + dummy\n");
+			return ret;
+		}
+	}
+
+	/* send/received the data */
+	if (op->data.nbytes) {
+		if (op->data.dir == SPI_MEM_DATA_IN)
+			rx_buf = op->data.buf.in;
+		else
+			tx_buf = op->data.buf.out;
+
+		spi->fmt_proto = op->data.buswidth;
+
+		ret = sifive_spi_xfer(dev, op->data.nbytes * 8,
+				      tx_buf, rx_buf, SPI_XFER_END);
+		if (ret) {
+			dev_err(dev, "failed to xfer data\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int sifive_spi_set_speed(struct udevice *bus, uint speed)
 {
 	struct sifive_spi *spi = dev_get_priv(bus);
@@ -309,6 +408,10 @@
 	/* Watermark interrupts are disabled by default */
 	writel(0, spi->regs + SIFIVE_SPI_REG_IE);
 
+	/* Default watermark FIFO threshold values */
+	writel(1, spi->regs + SIFIVE_SPI_REG_TXMARK);
+	writel(0, spi->regs + SIFIVE_SPI_REG_RXMARK);
+
 	/* Set CS/SCK Delays and Inactive Time to defaults */
 	writel(SIFIVE_SPI_DELAY0_CSSCK(1) | SIFIVE_SPI_DELAY0_SCKCS(1),
 	       spi->regs + SIFIVE_SPI_REG_DELAY0);
@@ -348,11 +451,16 @@
 	return 0;
 }
 
+static const struct spi_controller_mem_ops sifive_spi_mem_ops = {
+	.exec_op	= sifive_spi_exec_op,
+};
+
 static const struct dm_spi_ops sifive_spi_ops = {
 	.xfer		= sifive_spi_xfer,
 	.set_speed	= sifive_spi_set_speed,
 	.set_mode	= sifive_spi_set_mode,
 	.cs_info        = sifive_spi_cs_info,
+	.mem_ops	= &sifive_spi_mem_ops,
 };
 
 static const struct udevice_id sifive_spi_ids[] = {
diff --git a/drivers/timer/mtk_timer.c b/drivers/timer/mtk_timer.c
index b5e76bd..e99135e 100644
--- a/drivers/timer/mtk_timer.c
+++ b/drivers/timer/mtk_timer.c
@@ -71,6 +71,7 @@
 
 static const struct udevice_id mtk_timer_ids[] = {
 	{ .compatible = "mediatek,timer" },
+	{ .compatible = "mediatek,mt6577-timer" },
 	{ }
 };
 
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 6cafd24..bf06180 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -49,6 +49,7 @@
 config DESIGNWARE_WATCHDOG
 	bool "Designware watchdog timer support"
 	select HW_WATCHDOG if !WDT
+	default y if WDT && ROCKCHIP_RK3399
 	help
 	  Enable this to support Designware Watchdog Timer IP, present e.g.
 	  on Altera SoCFPGA SoCs.
diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c
index 669a323..b3c597e 100644
--- a/drivers/watchdog/mtk_wdt.c
+++ b/drivers/watchdog/mtk_wdt.c
@@ -143,6 +143,7 @@
 
 static const struct udevice_id mtk_wdt_ids[] = {
 	{ .compatible = "mediatek,wdt"},
+	{ .compatible = "mediatek,mt6589-wdt"},
 	{}
 };
 
diff --git a/fs/ext4/ext4_journal.c b/fs/ext4/ext4_journal.c
index f8524e5..0ceb73d 100644
--- a/fs/ext4/ext4_journal.c
+++ b/fs/ext4/ext4_journal.c
@@ -107,22 +107,18 @@
 	for (i = 0; i < MAX_JOURNAL_ENTRIES; i++) {
 		if (dirty_block_ptr[i]->blknr == -1)
 			break;
-		if (dirty_block_ptr[i]->buf)
-			free(dirty_block_ptr[i]->buf);
+		free(dirty_block_ptr[i]->buf);
 	}
 
 	for (i = 0; i < MAX_JOURNAL_ENTRIES; i++) {
 		if (journal_ptr[i]->blknr == -1)
 			break;
-		if (journal_ptr[i]->buf)
-			free(journal_ptr[i]->buf);
+		free(journal_ptr[i]->buf);
 	}
 
 	for (i = 0; i < MAX_JOURNAL_ENTRIES; i++) {
-		if (journal_ptr[i])
-			free(journal_ptr[i]);
-		if (dirty_block_ptr[i])
-			free(dirty_block_ptr[i]);
+		free(journal_ptr[i]);
+		free(dirty_block_ptr[i]);
 	}
 	gindex = 0;
 	gd_index = 0;
@@ -272,8 +268,7 @@
 	struct revoke_blk_list *next_node = NULL;
 
 	while (tmp_node != NULL) {
-		if (tmp_node->content)
-			free(tmp_node->content);
+		free(tmp_node->content);
 		tmp_node = tmp_node->next;
 	}
 
diff --git a/include/bedbug/type.h b/include/bedbug/type.h
index b7b447b..3754c7f 100644
--- a/include/bedbug/type.h
+++ b/include/bedbug/type.h
@@ -3,7 +3,7 @@
 
 /* Supporting routines */
 int bedbug_puts (const char *);
-void bedbug_init (void);
+int bedbug_init(void);
 void bedbug860_init (void);
 void do_bedbug_breakpoint (struct pt_regs *);
 void bedbug_main_loop (unsigned long, struct pt_regs *);
diff --git a/include/configs/grpeach.h b/include/configs/grpeach.h
index f1ea729..001e9d3 100644
--- a/include/configs/grpeach.h
+++ b/include/configs/grpeach.h
@@ -16,7 +16,6 @@
 
 /* Miscellaneous */
 #define CONFIG_SYS_PBSIZE	256
-#define CONFIG_SYS_ARM_CACHE_WRITETHROUGH
 #define CONFIG_CMDLINE_TAG
 
 /* Internal RAM Size (RZ/A1=3M, RZ/A1M=5M, RZ/A1H=10M) */
diff --git a/include/configs/mt7623.h b/include/configs/mt7623.h
index faab091..fe436cc 100644
--- a/include/configs/mt7623.h
+++ b/include/configs/mt7623.h
@@ -45,11 +45,13 @@
 #define CONFIG_SYS_SDRAM_BASE		0x80000000
 
 /* This is needed for kernel booting */
-#define FDT_HIGH			"fdt_high=0xac000000\0"
+#define FDT_HIGH			"0xac000000"
 
-/* Extra environment variables */
-#define CONFIG_EXTRA_ENV_SETTINGS	\
-	FDT_HIGH
+#define ENV_MEM_LAYOUT_SETTINGS				\
+	"fdt_high=" FDT_HIGH "\0"			\
+	"kernel_addr_r=0x84000000\0"			\
+	"fdt_addr_r=" FDT_HIGH "\0"			\
+	"fdtfile=mt7623n-bananapi-bpi-r2.dtb" "\0"
 
 /* Ethernet */
 #define CONFIG_IPADDR			192.168.1.1
@@ -57,4 +59,18 @@
 
 #define CONFIG_SYS_MMC_ENV_DEV		0
 
+#ifdef CONFIG_DISTRO_DEFAULTS
+
+#define BOOT_TARGET_DEVICES(func)	\
+		func(MMC, mmc, 1)
+
+#include <config_distro_bootcmd.h>
+
+/* Extra environment variables */
+#define CONFIG_EXTRA_ENV_SETTINGS	\
+	ENV_MEM_LAYOUT_SETTINGS		\
+	BOOTENV
+
+#endif /* ifdef CONFIG_DISTRO_DEFAULTS*/
+
 #endif
diff --git a/include/configs/pxa-common.h b/include/configs/pxa-common.h
index e25800a..2632d48 100644
--- a/include/configs/pxa-common.h
+++ b/include/configs/pxa-common.h
@@ -8,8 +8,6 @@
 #ifndef	__CONFIG_PXA_COMMON_H__
 #define	__CONFIG_PXA_COMMON_H__
 
-#define	CONFIG_SYS_ARM_CACHE_WRITETHROUGH
-
 /*
  * KGDB
  */
diff --git a/include/configs/rk3399_common.h b/include/configs/rk3399_common.h
index 89a8a44..f0ae6e6 100644
--- a/include/configs/rk3399_common.h
+++ b/include/configs/rk3399_common.h
@@ -48,6 +48,8 @@
 
 #define ENV_MEM_LAYOUT_SETTINGS \
 	"scriptaddr=0x00500000\0" \
+	"script_offset_f=0xffe000\0" \
+	"script_size_f=0x2000\0" \
 	"pxefile_addr_r=0x00600000\0" \
 	"fdt_addr_r=0x01f00000\0" \
 	"kernel_addr_r=0x02080000\0" \
@@ -58,6 +60,7 @@
 #endif
 
 #include <config_distro_bootcmd.h>
+#include <environment/distro/sf.h>
 #define CONFIG_EXTRA_ENV_SETTINGS \
 	ENV_MEM_LAYOUT_SETTINGS \
 	"fdtfile=" CONFIG_DEFAULT_FDT_FILE "\0" \
diff --git a/include/configs/rockchip-common.h b/include/configs/rockchip-common.h
index b55e09a..bf8c60d 100644
--- a/include/configs/rockchip-common.h
+++ b/include/configs/rockchip-common.h
@@ -41,11 +41,26 @@
 	#define BOOT_TARGET_DHCP(func)
 #endif
 
+#if CONFIG_IS_ENABLED(CMD_SF)
+	#define BOOT_TARGET_SF(func)	func(SF, sf, 0)
+#else
+	#define BOOT_TARGET_SF(func)
+#endif
+
+#ifdef CONFIG_ROCKCHIP_RK3399
 #define BOOT_TARGET_DEVICES(func) \
 	BOOT_TARGET_MMC(func) \
 	BOOT_TARGET_USB(func) \
 	BOOT_TARGET_PXE(func) \
+	BOOT_TARGET_DHCP(func) \
+	BOOT_TARGET_SF(func)
+#else
+#define BOOT_TARGET_DEVICES(func) \
+	BOOT_TARGET_MMC(func) \
+	BOOT_TARGET_USB(func) \
+	BOOT_TARGET_PXE(func) \
 	BOOT_TARGET_DHCP(func)
+#endif
 
 #ifdef CONFIG_ARM64
 #define ROOT_UUID "B921B045-1DF0-41C3-AF44-4C6F280D3FAE;\0"
diff --git a/include/environment/distro/sf.h b/include/environment/distro/sf.h
new file mode 100644
index 0000000..e793be0
--- /dev/null
+++ b/include/environment/distro/sf.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2020 Amarula Solutions(India)
+ *
+ * SF distro configurations.
+ */
+
+#ifndef __DISTRO_SF_CONFIG_H
+#define __DISTRO_SF_CONFIG_H
+
+#if CONFIG_IS_ENABLED(CMD_SF)
+#define BOOTENV_SHARED_SF(devtypel)				\
+	#devtypel "_boot=" 					\
+	"if " #devtypel " probe ${busnum}; then "		\
+		"devtype=" #devtypel "; "	  		\
+		"run scan_sf_for_scripts; "	  		\
+	"fi\0"
+#define BOOTENV_DEV_SF(devtypeu, devtypel, instance) 		\
+	"bootcmd_" #devtypel #instance "=" 			\
+		"busnum=" #instance "; " 			\
+		"run " #devtypel "_boot\0"
+#define BOOTENV_DEV_NAME_SF(devtypeu, devtypel, instance) 	\
+	#devtypel #instance " "
+#else
+#define BOOTENV_SHARED_SF(devtypel)
+#define BOOTENV_DEV_SF \
+	BOOT_TARGET_DEVICES_references_SF_without_CONFIG_CMD_SF
+#define BOOTENV_DEV_NAME_SF \
+	BOOT_TARGET_DEVICES_references_SF_without_CONFIG_CMD_SF
+
+#endif /* CONFIG_CMD_SF */
+
+#define BOOTENV_SF \
+	BOOTENV_SHARED_SF(sf) \
+	"scan_sf_for_scripts="					\
+		"${devtype} read ${scriptaddr} "		\
+			"${script_offset_f} ${script_size_f}; "	\
+		"source ${scriptaddr}; "			\
+		"echo SCRIPT FAILED: continuing...\0"
+
+#endif /* __DISTRO_SF_CONFIG_H */
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index ec144a0..233fdc3 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -22,6 +22,7 @@
 #define SNOR_MFR_INTEL		CFI_MFR_INTEL
 #define SNOR_MFR_ST		CFI_MFR_ST /* ST Micro <--> Micron */
 #define SNOR_MFR_MICRON		CFI_MFR_MICRON /* ST Micro <--> Micron */
+#define SNOR_MFR_ISSI		CFI_MFR_PMC
 #define SNOR_MFR_MACRONIX	CFI_MFR_MACRONIX
 #define SNOR_MFR_SPANSION	CFI_MFR_AMD
 #define SNOR_MFR_SST		CFI_MFR_SST
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index be01e1e..83eafb1 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -204,6 +204,7 @@
 extern const struct spinand_manufacturer gigadevice_spinand_manufacturer;
 extern const struct spinand_manufacturer macronix_spinand_manufacturer;
 extern const struct spinand_manufacturer micron_spinand_manufacturer;
+extern const struct spinand_manufacturer toshiba_spinand_manufacturer;
 extern const struct spinand_manufacturer winbond_spinand_manufacturer;
 
 /**
diff --git a/include/spi-mem.h b/include/spi-mem.h
index 36814ef..893f7bd 100644
--- a/include/spi-mem.h
+++ b/include/spi-mem.h
@@ -60,10 +60,12 @@
 /**
  * enum spi_mem_data_dir - describes the direction of a SPI memory data
  *			   transfer from the controller perspective
+ * @SPI_MEM_NO_DATA: no data transferred
  * @SPI_MEM_DATA_IN: data coming from the SPI memory
  * @SPI_MEM_DATA_OUT: data sent the SPI memory
  */
 enum spi_mem_data_dir {
+	SPI_MEM_NO_DATA,
 	SPI_MEM_DATA_IN,
 	SPI_MEM_DATA_OUT,
 };
diff --git a/lib/tiny-printf.c b/lib/tiny-printf.c
index 1138c70..8fc7e48 100644
--- a/lib/tiny-printf.c
+++ b/lib/tiny-printf.c
@@ -242,6 +242,7 @@
 				goto abort;
 			case 'u':
 			case 'd':
+			case 'i':
 				div = 1000000000;
 				if (islong) {
 					num = va_arg(va, unsigned long);
@@ -251,7 +252,7 @@
 					num = va_arg(va, unsigned int);
 				}
 
-				if (ch == 'd') {
+				if (ch != 'u') {
 					if (islong && (long)num < 0) {
 						num = -(long)num;
 						out(info, '-');
diff --git a/scripts/config_whitelist.txt b/scripts/config_whitelist.txt
index 9b9f7df..19c9218 100644
--- a/scripts/config_whitelist.txt
+++ b/scripts/config_whitelist.txt
@@ -1768,7 +1768,6 @@
 CONFIG_SYS_AMASK5
 CONFIG_SYS_AMASK6
 CONFIG_SYS_AMASK7
-CONFIG_SYS_ARM_CACHE_WRITETHROUGH
 CONFIG_SYS_AT91_CPU_NAME
 CONFIG_SYS_AT91_MAIN_CLOCK
 CONFIG_SYS_AT91_PLLA
diff --git a/test/py/tests/test_vboot.py b/test/py/tests/test_vboot.py
index e67f2b3..6b998cf 100644
--- a/test/py/tests/test_vboot.py
+++ b/test/py/tests/test_vboot.py
@@ -30,11 +30,16 @@
 import vboot_forge
 
 TESTDATA = [
-    ['sha1', '', False],
-    ['sha1', '-pss', False],
-    ['sha256', '', False],
-    ['sha256', '-pss', False],
-    ['sha256', '-pss', True],
+    ['sha1', '', None, False],
+    ['sha1', '', '-E -p 0x10000', False],
+    ['sha1', '-pss', None, False],
+    ['sha1', '-pss', '-E -p 0x10000', False],
+    ['sha256', '', None, False],
+    ['sha256', '', '-E -p 0x10000', False],
+    ['sha256', '-pss', None, False],
+    ['sha256', '-pss', '-E -p 0x10000', False],
+    ['sha256', '-pss', None, True],
+    ['sha256', '-pss', '-E -p 0x10000', True],
 ]
 
 @pytest.mark.boardspec('sandbox')
@@ -43,8 +48,8 @@
 @pytest.mark.requiredtool('fdtget')
 @pytest.mark.requiredtool('fdtput')
 @pytest.mark.requiredtool('openssl')
-@pytest.mark.parametrize("sha_algo,padding,required", TESTDATA)
-def test_vboot(u_boot_console, sha_algo, padding, required):
+@pytest.mark.parametrize("sha_algo,padding,sign_options,required", TESTDATA)
+def test_vboot(u_boot_console, sha_algo, padding, sign_options, required):
     """Test verified boot signing with mkimage and verification with 'bootm'.
 
     This works using sandbox only as it needs to update the device tree used
@@ -104,7 +109,7 @@
         util.run_and_log(cons, [mkimage, '-D', dtc_args, '-f',
                                 '%s%s' % (datadir, its), fit])
 
-    def sign_fit(sha_algo):
+    def sign_fit(sha_algo, options):
         """Sign the FIT
 
         Signs the FIT and writes the signature into it. It also writes the
@@ -113,10 +118,13 @@
         Args:
             sha_algo: Either 'sha1' or 'sha256', to select the algorithm to
                     use.
+            options: Options to provide to mkimage.
         """
+        args = [mkimage, '-F', '-k', tmpdir, '-K', dtb, '-r', fit]
+        if options:
+            args += options.split(' ')
         cons.log.action('%s: Sign images' % sha_algo)
-        util.run_and_log(cons, [mkimage, '-F', '-k', tmpdir, '-K', dtb,
-                                '-r', fit])
+        util.run_and_log(cons, args)
 
     def replace_fit_totalsize(size):
         """Replace FIT header's totalsize with something greater.
@@ -154,7 +162,7 @@
         util.run_and_log(cons, 'openssl req -batch -new -x509 -key %s%s.key '
                          '-out %s%s.crt' % (tmpdir, name, tmpdir, name))
 
-    def test_with_algo(sha_algo, padding):
+    def test_with_algo(sha_algo, padding, sign_options):
         """Test verified boot with the given hash algorithm.
 
         This is the main part of the test code. The same procedure is followed
@@ -163,6 +171,9 @@
         Args:
             sha_algo: Either 'sha1' or 'sha256', to select the algorithm to
                     use.
+            padding: Either '' or '-pss', to select the padding to use for the
+                    rsa signature algorithm.
+            sign_options: Options to mkimage when signing a fit image.
         """
         # Compile our device tree files for kernel and U-Boot. These are
         # regenerated here since mkimage will modify them (by adding a
@@ -176,7 +187,7 @@
         run_bootm(sha_algo, 'unsigned images', 'dev-', True)
 
         # Sign images with our dev keys
-        sign_fit(sha_algo)
+        sign_fit(sha_algo, sign_options)
         run_bootm(sha_algo, 'signed images', 'dev+', True)
 
         # Create a fresh .dtb without the public keys
@@ -187,7 +198,7 @@
         run_bootm(sha_algo, 'unsigned config', '%s+ OK' % sha_algo, True)
 
         # Sign images with our dev keys
-        sign_fit(sha_algo)
+        sign_fit(sha_algo, sign_options)
         run_bootm(sha_algo, 'signed config', 'dev+', True)
 
         cons.log.action('%s: Check signed config on the host' % sha_algo)
@@ -209,7 +220,7 @@
 
         # Create a new properly signed fit and replace header bytes
         make_fit('sign-configs-%s%s.its' % (sha_algo, padding))
-        sign_fit(sha_algo)
+        sign_fit(sha_algo, sign_options)
         bcfg = u_boot_console.config.buildconfig
         max_size = int(bcfg.get('config_fit_signature_max_size', 0x10000000), 0)
         existing_size = replace_fit_totalsize(max_size + 1)
@@ -240,7 +251,7 @@
             cons, [fit_check_sign, '-f', fit, '-k', dtb],
             1, 'Failed to verify required signature')
 
-    def test_required_key(sha_algo, padding):
+    def test_required_key(sha_algo, padding, sign_options):
         """Test verified boot with the given hash algorithm.
 
         This function tests if U-Boot rejects an image when a required key isn't
@@ -248,6 +259,9 @@
 
         Args:
             sha_algo: Either 'sha1' or 'sha256', to select the algorithm to use
+            padding: Either '' or '-pss', to select the padding to use for the
+                    rsa signature algorithm.
+            sign_options: Options to mkimage when signing a fit image.
         """
         # Compile our device tree files for kernel and U-Boot. These are
         # regenerated here since mkimage will modify them (by adding a
@@ -260,12 +274,12 @@
         # Build the FIT with prod key (keys required) and sign it. This puts the
         # signature into sandbox-u-boot.dtb, marked 'required'
         make_fit('sign-configs-%s%s-prod.its' % (sha_algo, padding))
-        sign_fit(sha_algo)
+        sign_fit(sha_algo, sign_options)
 
         # Build the FIT with dev key (keys NOT required). This adds the
         # signature into sandbox-u-boot.dtb, NOT marked 'required'.
         make_fit('sign-configs-%s%s.its' % (sha_algo, padding))
-        sign_fit(sha_algo)
+        sign_fit(sha_algo, sign_options)
 
         # So now sandbox-u-boot.dtb two signatures, for the prod and dev keys.
         # Only the prod key is set as 'required'. But FIT we just built has
@@ -297,9 +311,9 @@
         old_dtb = cons.config.dtb
         cons.config.dtb = dtb
         if required:
-            test_required_key(sha_algo, padding)
+            test_required_key(sha_algo, padding, sign_options)
         else:
-            test_with_algo(sha_algo, padding)
+            test_with_algo(sha_algo, padding, sign_options)
     finally:
         # Go back to the original U-Boot with the correct dtb.
         cons.config.dtb = old_dtb
diff --git a/tools/fit_image.c b/tools/fit_image.c
index 4aeabbc..1e0f1e9 100644
--- a/tools/fit_image.c
+++ b/tools/fit_image.c
@@ -17,6 +17,7 @@
 #include "fit_common.h"
 #include "mkimage.h"
 #include <image.h>
+#include <string.h>
 #include <stdarg.h>
 #include <version.h>
 #include <u-boot/crc.h>
@@ -434,7 +435,7 @@
 	int image_number;
 	int align_size;
 
-	align_size = params->bl_len ? params->bl_len : 4;
+	align_size = params->bl_len ? params->bl_len : 1;
 	fd = mmap_fdt(params->cmdname, fname, 0, &fdt, &sbuf, false, false);
 	if (fd < 0)
 		return -EIO;
@@ -492,7 +493,6 @@
 	fdt_pack(fdt);
 
 	new_size = fdt_totalsize(fdt);
-	new_size = ALIGN(new_size, align_size);
 	fdt_set_totalsize(fdt, new_size);
 	debug("Size reduced from %x to %x\n", fit_size, fdt_totalsize(fdt));
 	debug("External data size %x\n", buf_ptr);
@@ -744,6 +744,9 @@
 		snprintf(cmd, sizeof(cmd), "cp \"%s\" \"%s\"",
 			 params->imagefile, tmpfile);
 	}
+	if (strlen(cmd) >= MKIMAGE_MAX_DTC_CMDLINE_LEN - 1) {
+		fprintf(stderr, "WARNING: command-line for FIT creation might be truncated and will probably fail.\n");
+	}
 
 	if (*cmd && system(cmd) == -1) {
 		fprintf (stderr, "%s: system(%s) failed: %s\n",
diff --git a/tools/mkimage.h b/tools/mkimage.h
index 0254af5..5b096a5 100644
--- a/tools/mkimage.h
+++ b/tools/mkimage.h
@@ -42,6 +42,6 @@
 #define MKIMAGE_TMPFILE_SUFFIX		".tmp"
 #define MKIMAGE_MAX_TMPFILE_LEN		256
 #define MKIMAGE_DEFAULT_DTC_OPTIONS	"-I dts -O dtb -p 500"
-#define MKIMAGE_MAX_DTC_CMDLINE_LEN	512
+#define MKIMAGE_MAX_DTC_CMDLINE_LEN	2 * MKIMAGE_MAX_TMPFILE_LEN + 35
 
 #endif /* _MKIIMAGE_H_ */