Re: [Qemu-devel] [RFC v3 06/15] hw/arm/virt: Allocate device_memory

[Igor Mammedov <imammedo@redhat.com>]

On Tue,  3 Jul 2018 09:19:49 +0200
Eric Auger <eric.auger@redhat.com> wrote:

> We define a new hotpluggable RAM region (aka. device memory).
> Its base is 2TB GPA. This obviously requires 42b IPA support
> in KVM/ARM, FW and guest kernel. At the moment the device
> memory region is max 2TB.
> 
> This is largely inspired of device memory initialization in
> pc machine code.
> 
> Signed-off-by: Eric Auger <eric.auger@redhat.com>
> Signed-off-by: Kwangwoo Lee <kwangwoo.lee@sk.com>
> ---
>  hw/arm/virt.c         | 104 ++++++++++++++++++++++++++++++++++++--------------
>  include/hw/arm/arm.h  |   2 +
>  include/hw/arm/virt.h |   1 +
>  3 files changed, 79 insertions(+), 28 deletions(-)
> 
> diff --git a/hw/arm/virt.c b/hw/arm/virt.c
> index 5a4d0bf..6fefb78 100644
> --- a/hw/arm/virt.c
> +++ b/hw/arm/virt.c
> @@ -59,6 +59,7 @@
>  #include "qapi/visitor.h"
>  #include "standard-headers/linux/input.h"
>  #include "hw/arm/smmuv3.h"
> +#include "hw/acpi/acpi.h"
>  
>  #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \
>      static void virt_##major##_##minor##_class_init(ObjectClass *oc, \
> @@ -94,34 +95,25 @@
>  
>  #define PLATFORM_BUS_NUM_IRQS 64
>  
> -/* RAM limit in GB. Since VIRT_MEM starts at the 1GB mark, this means
> - * RAM can go up to the 256GB mark, leaving 256GB of the physical
> - * address space unallocated and free for future use between 256G and 512G.
> - * If we need to provide more RAM to VMs in the future then we need to:
> - *  * allocate a second bank of RAM starting at 2TB and working up
> - *  * fix the DT and ACPI table generation code in QEMU to correctly
> - *    report two split lumps of RAM to the guest
> - *  * fix KVM in the host kernel to allow guests with >40 bit address spaces
> - * (We don't want to fill all the way up to 512GB with RAM because
> - * we might want it for non-RAM purposes later. Conversely it seems
> - * reasonable to assume that anybody configuring a VM with a quarter
> - * of a terabyte of RAM will be doing it on a host with more than a
> - * terabyte of physical address space.)
> - */
> -#define RAMLIMIT_GB 255
> -#define RAMLIMIT_BYTES (RAMLIMIT_GB * 1024ULL * 1024 * 1024)
> +#define SZ_64K 0x10000
> +#define SZ_1G (1024ULL * 1024 * 1024)
>  
>  /* Addresses and sizes of our components.
> - * 0..128MB is space for a flash device so we can run bootrom code such as UEFI.
> - * 128MB..256MB is used for miscellaneous device I/O.
> - * 256MB..1GB is reserved for possible future PCI support (ie where the
> - * PCI memory window will go if we add a PCI host controller).
> - * 1GB and up is RAM (which may happily spill over into the
> - * high memory region beyond 4GB).
> - * This represents a compromise between how much RAM can be given to
> - * a 32 bit VM and leaving space for expansion and in particular for PCI.
> - * Note that devices should generally be placed at multiples of 0x10000,
> + * 0..128MB is space for a flash device so we can run bootrom code such as UEFI,
> + * 128MB..256MB is used for miscellaneous device I/O,
> + * 256MB..1GB is used for PCI host controller,
> + * 1GB..256GB is RAM (not hotpluggable),
> + * 256GB..512GB: is left for device I/O (non RAM purpose),
> + * 512GB..1TB: high mem PCI MMIO region,
> + * 2TB..4TB is used for hot-pluggable DIMM (assumes 42b GPA is supported).
> + *
> + * Note that IO devices should generally be placed at multiples of 0x10000,
>   * to accommodate guests using 64K pages.
> + *
> + * Conversely it seems reasonable to assume that anybody configuring a VM
> + * with a quarter of a terabyte of RAM will be doing it on a host with more
> + * than a terabyte of physical address space.)
> + *
>   */
>  static const MemMapEntry a15memmap[] = {
>      /* Space up to 0x8000000 is reserved for a boot ROM */
> @@ -148,12 +140,13 @@ static const MemMapEntry a15memmap[] = {
>      [VIRT_PCIE_MMIO] =          { 0x10000000, 0x2eff0000 },
>      [VIRT_PCIE_PIO] =           { 0x3eff0000, 0x00010000 },
>      [VIRT_PCIE_ECAM] =          { 0x3f000000, 0x01000000 },
> -    [VIRT_MEM] =                { 0x40000000, RAMLIMIT_BYTES },
> +    [VIRT_MEM] =                { SZ_1G , 255 * SZ_1G },
>      /* Additional 64 MB redist region (can contain up to 512 redistributors) */
>      [VIRT_GIC_REDIST2] =        { 0x4000000000ULL, 0x4000000 },
>      [VIRT_PCIE_ECAM_HIGH] =     { 0x4010000000ULL, 0x10000000 },
>      /* Second PCIe window, 512GB wide at the 512GB boundary */
> -    [VIRT_PCIE_MMIO_HIGH] =   { 0x8000000000ULL, 0x8000000000ULL },
> +    [VIRT_PCIE_MMIO_HIGH] =     { 512 * SZ_1G, 512 * SZ_1G },
> +    [VIRT_HOTPLUG_MEM] =        { 2048 * SZ_1G, 2048 * SZ_1G },
>  };
>  
>  static const int a15irqmap[] = {
> @@ -1223,6 +1216,58 @@ static void create_secure_ram(VirtMachineState *vms,
>      g_free(nodename);
>  }
>  
> +static void create_device_memory(VirtMachineState *vms, MemoryRegion *sysmem)
> +{
> +    MachineState *ms = MACHINE(vms);
> +    uint64_t device_memory_size;
> +    uint64_t align = SZ_64K;
> +
> +    /* always allocate the device memory information */
> +    ms->device_memory = g_malloc0(sizeof(*ms->device_memory));
> +
> +    if (vms->max_vm_phys_shift < 42) {
> +        /* device memory starts at 2TB whereas this VM supports less than
> +         * 2TB GPA */
> +        if (ms->maxram_size > ms->ram_size || ms->ram_slots) {
> +            MachineClass *mc = MACHINE_GET_CLASS(ms);
> +
> +            error_report("\"-memory 'slots|maxmem'\" is not supported by %s "
> +                         "since KVM does not support more than 41b IPA",
> +                         mc->name);
> +            exit(EXIT_FAILURE);
> +        }
> +        return;
> +    }
> +
> +    if (ms->ram_slots > ACPI_MAX_RAM_SLOTS) {
> +        error_report("unsupported number of memory slots: %"PRIu64,
> +                     ms->ram_slots);
> +        exit(EXIT_FAILURE);
> +    }
> +
> +    if (QEMU_ALIGN_UP(ms->maxram_size, align) != ms->maxram_size) {
> +        error_report("maximum memory size must be aligned to multiple of 0x%"
> +                     PRIx64, align);
> +            exit(EXIT_FAILURE);
> +    }
> +
> +    ms->device_memory->base = vms->memmap[VIRT_HOTPLUG_MEM].base;
> +    device_memory_size = ms->maxram_size - ms->ram_size;
> +
> +    if (device_memory_size > vms->memmap[VIRT_HOTPLUG_MEM].size) {
> +        error_report("unsupported amount of maximum memory: " RAM_ADDR_FMT,
> +                         ms->maxram_size);
> +        exit(EXIT_FAILURE);
> +    }
> +
> +    memory_region_init(&ms->device_memory->mr, OBJECT(vms),
> +                       "device-memory", device_memory_size);
> +    memory_region_add_subregion(sysmem, ms->device_memory->base,
> +                                &ms->device_memory->mr);

> +    vms->bootinfo.device_memory_start = ms->device_memory->base;
> +    vms->bootinfo.device_memory_size = device_memory_size;
why do we need duplicate it in bootinfo?
(I'd try avoid using bootinfo and use original source instead
where it's needed)


> +}
> +
>  static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size)
>  {
>      const VirtMachineState *board = container_of(binfo, VirtMachineState,
> @@ -1430,7 +1475,8 @@ static void machvirt_init(MachineState *machine)
>      vms->smp_cpus = smp_cpus;
>  
>      if (machine->ram_size > vms->memmap[VIRT_MEM].size) {
> -        error_report("mach-virt: cannot model more than %dGB RAM", RAMLIMIT_GB);
> +        error_report("mach-virt: cannot model more than %dGB RAM",
> +                     (int)(vms->memmap[VIRT_MEM].size / SZ_1G));
>          exit(1);
>      }
>  
> @@ -1525,6 +1571,8 @@ static void machvirt_init(MachineState *machine)
>                                           machine->ram_size);
>      memory_region_add_subregion(sysmem, vms->memmap[VIRT_MEM].base, ram);
>  
> +    create_device_memory(vms, sysmem);
> +
>      create_flash(vms, sysmem, secure_sysmem ? secure_sysmem : sysmem);
>  
>      create_gic(vms, pic);
> diff --git a/include/hw/arm/arm.h b/include/hw/arm/arm.h
> index ffed392..76269e6 100644
> --- a/include/hw/arm/arm.h
> +++ b/include/hw/arm/arm.h
> @@ -116,6 +116,8 @@ struct arm_boot_info {
>      bool secure_board_setup;
>  
>      arm_endianness endianness;
> +    hwaddr device_memory_start;
> +    hwaddr device_memory_size;
>  };
>  
>  /**
> diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h
> index 91f6de2..173938d 100644
> --- a/include/hw/arm/virt.h
> +++ b/include/hw/arm/virt.h
> @@ -78,6 +78,7 @@ enum {
>      VIRT_GPIO,
>      VIRT_SECURE_UART,
>      VIRT_SECURE_MEM,
> +    VIRT_HOTPLUG_MEM,
>  };
>  
>  typedef enum VirtIOMMUType {