init.s

// kernel entry point
// largely nicked from https://github.com/mit-pdos/xv6-riscv/blob/riscv/kernel/entry.S
.data
.globl STACKS
.text
.section .text.first
.globl start
.globl _entry
// _entry(mhartid: usize, dtb: *const u8)
_entry:
    // we arrive here, in machine mode, once qemu jumps to the start of memory

    // set up a stack
    la sp, STACKS
    li t0, 16384     // use 16k stacks

    // we want to get the pointer to the top of the (descending) stack
    // thus we want 16k * (hartid + 1)
    addi t1, a0, 1
    mul t0, t0, t1
    add sp, sp, t0

    call startup
spin:
    j spin // startup() will not return
.text

Makefile

LLVM = /usr
QEMU = /opt/qemu/bin/qemu-system-riscv64
TARGETFLAGS = --target=riscv64-none-unknown-elf -march=rv64imac
CFLAGS =  $(TARGETFLAGS) -mno-relax -fPIC -g
QEMUOPTS = -machine virt -bios none -kernel kern -m 128M \
		   			-nographic -s -S

LINKFLAGS = $(TARGETFLAGS) -fuse-ld=lld -nostdlib -nodefaultlibs \
			-Wl,-Tshoo.ld
CC = $(LLVM)/bin/clang

kern: init.o start.o
	$(CC) $(LINKFLAGS) $^ -o $@

qemu: kern
	$(QEMU) $(QEMUOPTS)
%.o: %.s
	$(CC) $(CFLAGS) -c $^

.PHONY: clean qemu
clean:
	rm *.o kern

shoo.ld

OUTPUT_ARCH("riscv64")
ENTRY(_entry)

SECTIONS {
    /* VIRT_DRAM */
    . = 0x80000000;

    .text : {
        *(.text.first)
        *(.text .text.*)
        . = ALIGN(0x1000);
    }

    .rodata ALIGN(0x1000) : {
        . = ALIGN(16);
        PROVIDE(srodata = .);
        *(.srodata .srodata.*)
        . = ALIGN(16);
        *(.rodata .rodata.*)
        . = ALIGN(0x1000);
        PROVIDE(erodata = .);
    }

    .data ALIGN(0x1000) : {
        PROVIDE(srwdata = .);
        *(.sdata .sdata.*)
        . = ALIGN(16);
        *(.data .data.*)
    }

    .bss ALIGN(0x1000) : {
        . = ALIGN(16);
        *(.sbss .sbss.*)
        . = ALIGN(16);
        *(.bss .bss.*)
    }
}

start.c

char STACKS[4*4096];
volatile int i1 = 0;
volatile int i2 = 0;
volatile int i3 = 0;

void fn3(void) {
    i3 = 10;
}

void fn2(void) {
    i2 = 3;
    fn3();
}

void fn1(void) {
    fn2();
    fn2();
    i1 = 18;
}

void startup(void) {
    fn1();
    while (1) {}
}