Is it good that clang generates so much code for div64, even with -O3?

Question

I am playing with code from https://github.com/torvalds/linux/blob/master/lib/math/div64.c using https://godbolt.org/, targeting ARM Cortex-M7 microcontroller.

clang generates much more code (208 lines of assembly), comparing to gcc (69 lines). I am using -O3 and it should unroll/expand/etc, but... I am not sure if it is good in this case.

Don't know will it be helpful or not, but:
1) removing 1st or 2nd loop makes the result similar to produced by gcc;
2) clang 5.0.0 creates much smaller code.

Here is the code (below there is also the link to configured example):

unsigned int div64_32(unsigned long long * n, unsigned int base)
{
    unsigned long long rem = *n;
    unsigned long long b = base;
    unsigned long long res, d = 1;
    unsigned int high = rem >> 32;

    /* Reduce the thing a bit first */
    res = 0;
    if (high >= base) {
        high /= base;
        res = (unsigned long long) high << 32;
        rem -= (unsigned long long) (high*base) << 32;
    }

    while ((long long)b > 0 && b < rem) {
        b = b+b;
        d = d+d;
    }

    do {
        if (rem >= b) {
            rem -= b;
            res += d;
        }
        b >>= 1;
        d >>= 1;
    } while (d);

    *n = res;
    return rem;
}

Options for both compilers:
ARM GCC 7.2.1 (none): -O3 -mcpu=cortex-m7 -mthumb -mfloat-abi=hard -mfpu=vfpv4
x86-x64 clang (trunk): -O3 -mcpu=cortex-m7 -mthumb -mfloat-abi=hard -mfpu=vfpv4 -target armv7m-none-eabi

And finally the link to example: link

Update
I made tests on NXP Kinetis KV58. Frequency 240 MHz, all code relocated to I-TCM.
Results, measured by oscilloscope:

        run 1     run 2
iar:   27.2 ms   17.6 ms
clang: 29.6 ms   19.2 ms
gcc:   22.1 ms   14.0 ms

run-1 with n *= 123 (see code below)
run-2 with n *= 127

I didn't compile code for clang and gcc myself, just copy&paste it from website. I also made changes to GCC code, because compiler did not recognize instructions (also see comments to the question):
ldrd r0, [r0] (line 9) => ldrd r0, r1, [r0])
strd r6, [ip] (line 55) => strd r6, r7, [r12])

void test()
{
    debug_pin(0, 0); // test pin 0: set LOW
    for (int i = 0; i < 1000; i++);

    debug_pin(0, 1); // test pin 0: set HIGH

    unsigned long long n = 54321, base = 123;
    for (int i = 0; i < 10000; i++)
    {
        base = div64_32_iar(&n, base);

        n += 65432;
        n *= 127; // 1st test was with 123
        base += 123;
    }
    debug_pin(0, 0);

    for (int i = 0; i < 1000; i++);

    debug_pin(0, 1);
    n = 54321, base = 123;
    for (int i = 0; i < 10000; i++)
    {
        base = div64_32_clang(&n, base);

        n += 65432;
        n *= 127; // 1st test was with 123
        base += 123;
    }
    debug_pin(0, 0);

    for (int i = 0; i < 1000; i++);

    debug_pin(0, 1);
    n = 54321, base = 123;
    for (int i = 0; i < 10000; i++)
    {
        base = div64_32_gcc(&n, base);

        n += 65432;
        n *= 127; // 1st test was with 123
        base += 123;
    }
    debug_pin(0, 0);
}