Copy minimal example to make bootloader

.gdbinit

@@ -0,0 +1,2 @@
+tar ext localhost:3333
+load

Makefile

@@ -0,0 +1,25 @@
+.PHONY: all clean
+
+RV_ARCH = rv32imacxw
+
+CC = riscv-none-elf-gcc
+OBJDUMP = riscv-none-elf-objdump
+CFLAGS = -ggdb3 -Os -march=$(RV_ARCH) -ffunction-sections -fdata-sections
+LDFLAGS = -ggdb3 -march=$(RV_ARCH) -Wl,--gc-sections --specs=nosys.specs
+
+all: bootloader.elf
+
+bootloader.elf: startup.o bootloader.o
+
+%.elf: linker.lds
+	$(CC) -Xlinker -Map=$(@:.elf=.map) -Wl,--script=linker.lds -nostartfiles -o $@ $(filter-out linker.lds,$+)
+	$(OBJDUMP) -xdsS $@ >$(@:.elf=.dump)
+
+%.o: %.S
+	$(CC) $(CFLAGS) -c -o $@ $<
+
+%.o: %.c
+	$(CC) $(CFLAGS) -c -o $@ $<
+
+clean:
+	rm -f *.o *.elf *.map *.dump

bootloader.c

@@ -0,0 +1,27 @@
+#include <stdint.h>
+
+#pragma GCC diagnostic ignored "-Wprio-ctor-dtor"
+__attribute__((constructor(0))) static void setup_qingke() {
+    asm volatile(
+        // Undocumented "Configure pipelining and instruction prediction"
+        "li t0, 0x1f\n"
+        "csrw 0xbc0, t0\n"
+    );
+}
+
+#define R32_RCC_APB2PCENR   (*(volatile uint32_t*)0x40021018)
+#define R32_GPIOA_CFGLR     (*(volatile uint32_t*)0x40010800)
+#define R32_GPIOA_BSHR      (*(volatile uint32_t*)0x40010810)
+
+int main(void) {
+    R32_RCC_APB2PCENR |= 1 << 2;
+    R32_GPIOA_CFGLR = (R32_GPIOA_CFGLR & ~0xf) | (0b0010 << 0);
+    while (1) {
+        R32_GPIOA_BSHR = 1 << 0;
+        for (int i = 0; i < 500000; i++)
+            asm volatile("");
+        R32_GPIOA_BSHR = 1 << 16;
+        for (int i = 0; i < 500000; i++)
+            asm volatile("");
+    }
+}

linker.lds

@@ -0,0 +1,99 @@
+ENTRY( _start )
+
+__stack_size = 512;
+PROVIDE( _stack_size = __stack_size );
+
+MEMORY
+{
+    /* CH32V20x_D6 -> 10 KB SRAM */
+    /* allow full flash (incl. non-zero-wait) */
+    FLASH (rx) : ORIGIN = 0x00000000, LENGTH = 224K
+    RAM (xrw) : ORIGIN = 0x20000000, LENGTH = 10K
+}
+
+SECTIONS
+{
+    .vector :
+    {
+        *(.vector);
+        . = ALIGN(4);
+    } >FLASH
+    
+    .text :
+    {
+        *(.text)
+        *(.text.*)
+        *(.rodata)
+        *(.rodata*)
+        *(.gnu.linkonce.t.*)
+        . = ALIGN(4);
+    } >FLASH
+
+    .preinit_array :
+    {
+        PROVIDE_HIDDEN (__preinit_array_start = .);
+        KEEP (*(.preinit_array))
+        PROVIDE_HIDDEN (__preinit_array_end = .);
+    } >FLASH
+
+    .init_array :
+    {
+        PROVIDE_HIDDEN (__init_array_start = .);
+        KEEP (*(SORT_BY_INIT_PRIORITY(.init_array.*) SORT_BY_INIT_PRIORITY(.ctors.*)))
+        KEEP (*(.init_array EXCLUDE_FILE (*crtbegin.o *crtbegin?.o *crtend.o *crtend?.o ) .ctors))
+        PROVIDE_HIDDEN (__init_array_end = .);
+    } >FLASH
+
+    .fini_array :
+    {
+        PROVIDE_HIDDEN (__fini_array_start = .);
+        KEEP (*(SORT_BY_INIT_PRIORITY(.fini_array.*) SORT_BY_INIT_PRIORITY(.dtors.*)))
+        KEEP (*(.fini_array EXCLUDE_FILE (*crtbegin.o *crtbegin?.o *crtend.o *crtend?.o ) .dtors))
+        PROVIDE_HIDDEN (__fini_array_end = .);
+    } >FLASH
+
+    PROVIDE(_data_lma = .);
+
+    .data :
+    {
+        PROVIDE(_data_vma = .);
+        *(.gnu.linkonce.r.*)
+        *(.data .data.*)
+        *(.gnu.linkonce.d.*)
+        . = ALIGN(4);
+        PROVIDE( __global_pointer$ = . + 0x800 );
+        *(.sdata .sdata.*)
+        *(.sdata2.*)
+        *(.gnu.linkonce.s.*)
+        . = ALIGN(4);
+        *(.srodata.cst16)
+        *(.srodata.cst8)
+        *(.srodata.cst4)
+        *(.srodata.cst2)
+        *(.srodata .srodata.*)
+        . = ALIGN(4);
+        PROVIDE( _edata = .);
+    } >RAM AT>FLASH
+
+    .bss :
+    {
+        PROVIDE( _sbss = .);
+        *(.sbss*)
+        *(.gnu.linkonce.sb.*)
+        *(.bss*)
+        *(.gnu.linkonce.b.*)
+        *(COMMON*)
+        . = ALIGN(4);
+        PROVIDE( _ebss = .);
+    } >RAM
+
+    PROVIDE( _end = _ebss);
+
+    .stack ORIGIN(RAM) + LENGTH(RAM) - __stack_size :
+    {
+        PROVIDE( _heap_end = . );
+        PROVIDE( _susrstack = . );
+        . = . + __stack_size;
+        PROVIDE( _eusrstack = .);
+    } >RAM 
+}

startup.S

@@ -0,0 +1,77 @@
+.section .vector,"ax",@progbits
+.align 1
+
+.global _start
+_start:
+    // Set up global pointer
+.option push
+.option norelax
+    la gp, __global_pointer$
+.option pop
+
+    // Load data section from flash to RAM
+    la a0, _data_lma
+    la a1, _data_vma
+    la a2, _edata
+    bgeu a1, a2, 2f
+1:
+    lw t0, (a0)
+    sw t0, (a1)
+    addi a0, a0, 4
+    addi a1, a1, 4
+    bltu a1, a2, 1b
+2:
+
+    // Clear bss section
+    la a0, _sbss
+    la a1, _ebss
+    bgeu a0, a1, 2f
+1:
+    sw zero, (a0)
+    addi a0, a0, 4
+    bltu a0, a1, 1b
+2:
+
+    // Call preinit array functions
+    la s0, __preinit_array_start
+    la s1, __preinit_array_end
+    bgeu s0, s1, 2f
+1:
+    lw t0, (s0)
+    jalr t0
+    addi s0, s0, 4
+    bltu s0, s1, 1b
+2:
+
+    // Call init array functions
+    la s0, __init_array_start
+    la s1, __init_array_end
+    bgeu s0, s1, 2f
+1:
+    lw t0, (s0)
+    jalr t0
+    addi s0, s0, 4
+    bltu s0, s1, 1b
+2:
+
+    // Invoke main with a possible mode switch
+    la ra, 1f
+    la t0, main
+    csrw mepc, t0
+    mret
+
+1:
+    // Return from main, call fini array functions
+    la s0, __fini_array_start
+    la s1, __fini_array_end
+    bgeu s0, s1, 2f
+1:
+    lw t0, (s0)
+    jalr t0
+    addi s0, s0, 4
+    bltu s0, s1, 1b
+2:
+
+    // Finally, loop infinitely
+    wfi
+    j 2b