Re: [Qemu-devel] [PULL v2 8/8] hw/mips: MIPS Boston board support

[Peter Maydell]

On 22 February 2017 at 00:21, Yongbok Kim <address@hidden> wrote:
> From: Paul Burton <address@hidden>
>
> Introduce support for emulating the MIPS Boston development board. The
> Boston board is built around an FPGA & 3 PCIe controllers, one of which
> is connected to an Intel EG20T Platform Controller Hub. It is used
> during the development & debug of new CPUs and the software intended to
> run on them, and is essentially the successor to the older MIPS Malta
> board.
>
> This patch does not implement the EG20T, instead connecting an already
> supported ICH-9 AHCI controller. Whilst this isn't accurate it's enough
> for typical stock Boston software (eg. Linux kernels) to work with hard
> disks given that both the ICH-9 & EG20T implement the AHCI
> specification.
>
> Boston boards typically boot kernels in the FIT image format, and this
> patch will treat kernels provided to QEMU as such. When loading a kernel
> directly, the board code will generate minimal firmware much as the
> Malta board code does. This firmware will set up the CM, CPC & GIC
> register base addresses then set argument registers & jump to the kernel
> entry point. Alternatively, bootloader code may be loaded using the bios
> argument in which case no firmware will be generated & execution will
> proceed from the start of the boot code at the default MIPS boot
> exception vector (offset 0x1fc00000 into (c)kseg1).
>
> Currently real Boston boards are always used with FPGA bitfiles that
> include a Global Interrupt Controller (GIC), so the interrupt
> configuration is only defined for such cases. Therefore the board will
> only allow use of CPUs which implement the CPS components, including the
> GIC, and will otherwise exit with a message.
>
> +static void boston_mach_class_init(MachineClass *mc)
> +{
> +    mc->desc = "MIPS Boston";
> +    mc->init = boston_mach_init;
> +    mc->block_default_type = IF_IDE;
> +    mc->default_ram_size = 2 * G_BYTE;
> +    mc->max_cpus = 16;
> +}

I only just noticed, but this breaks "make check" on 32-bit hosts:

TEST: tests/qom-test... (pid=16740)
  /mips64el/qom/boston:
qemu-system-mips64el: at most 2047 MB RAM can be simulated
Broken pipe
FAIL

because vl.c has
        /* On 32-bit hosts, QEMU is limited by virtual address space */
        if (ram_size > (2047 << 20) && HOST_LONG_BITS == 32) {
            error_report("at most 2047 MB RAM can be simulated");
            exit(1);
        }

Unfortunately I didn't notice before I pushed your pull request.
Luckily this is the last patch in the pullreq, so I can just
revert this one commit (d3473e147a754e999718bf6fcb015d9978c6a1ee)...

Please fix the board model patch and resend it. You'll need
the board to default to a ram size that works on all hosts.

(I'm taking the revert option because we're getting pretty
close to freeze and I have a bunch of pull requests in the
queue that I'd prefer not to delay while we fix this up.)

thanks
-- PMM