Re: [Qemu-devel] [PATCH] q35: fix mmconfig and PCI0._CRS

[Igor Mammedov <imammedo@redhat.com>]

On Tue, 28 May 2019 22:43:31 +0200
Gerd Hoffmann <kraxel@redhat.com> wrote:

> This patch changes the handling of the mmconfig area.  Thanks to the
> pci(e) expander devices we already have the logic to exclude address
> ranges from PCI0._CRS.  We can simply add the mmconfig address range
> to the list get it excluded as well.
> 
> With that in place we can go with a fixed pci hole which covers the
> whole area from the end of (low) ram to the ioapic.
> 
> This will make the whole logic alot less fragile.  No matter where the
> firmware places the mmconfig xbar, things should work correctly.  The
> guest also gets a bit more PCI address space (seabios boot):
> 
>     # cat /proc/iomem
>     [ ... ]
>     7ffdd000-7fffffff : reserved
>     80000000-afffffff : PCI Bus 0000:00            <<-- this is new
>     b0000000-bfffffff : PCI MMCONFIG 0000 [bus 00-ff]
>       b0000000-bfffffff : reserved
>     c0000000-febfffff : PCI Bus 0000:00
>       f8000000-fbffffff : 0000:00:01.0
>     [ ... ]
> 
> So this is a guest visible change.
> 
> Cc: László Érsek <lersek@redhat.com>
> Cc: Igor Mammedov <imammedo@redhat.com>
> Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

Reviewed-by: Igor Mammedov <imammedo@redhat.com>

> ---
>  hw/i386/acpi-build.c | 14 ++++++++++++++
>  hw/pci-host/q35.c    | 31 ++++++++-----------------------
>  2 files changed, 22 insertions(+), 23 deletions(-)
> 
> diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
> index 0d78d738948c..abb0e0ce9f27 100644
> --- a/hw/i386/acpi-build.c
> +++ b/hw/i386/acpi-build.c
> @@ -122,6 +122,8 @@ typedef struct FwCfgTPMConfig {
>      uint8_t tpmppi_version;
>  } QEMU_PACKED FwCfgTPMConfig;
>  
> +static bool acpi_get_mcfg(AcpiMcfgInfo *mcfg);
> +
>  static void init_common_fadt_data(Object *o, AcpiFadtData *data)
>  {
>      uint32_t io = object_property_get_uint(o, ACPI_PM_PROP_PM_IO_BASE, NULL);
> @@ -1807,6 +1809,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
>      CrsRangeSet crs_range_set;
>      PCMachineState *pcms = PC_MACHINE(machine);
>      PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(machine);
> +    AcpiMcfgInfo mcfg;
>      uint32_t nr_mem = machine->ram_slots;
>      int root_bus_limit = 0xFF;
>      PCIBus *bus = NULL;
> @@ -1921,6 +1924,17 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
>          }
>      }
>  
> +    /*
> +     * At this point crs_range_set has all the ranges used by pci
> +     * busses *other* than PCI0.  These ranges will be excluded from
> +     * the PCI0._CRS.  Add mmconfig to the set so it will be excluded
> +     * too.
> +     */
> +    if (acpi_get_mcfg(&mcfg)) {
> +        crs_range_insert(crs_range_set.mem_ranges,
> +                         mcfg.base, mcfg.base + mcfg.size - 1);
> +    }
> +
>      scope = aml_scope("\\_SB.PCI0");
>      /* build PCI0._CRS */
>      crs = aml_resource_template();
> diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c
> index 960939f5ed3e..72093320befe 100644
> --- a/hw/pci-host/q35.c
> +++ b/hw/pci-host/q35.c
> @@ -258,15 +258,6 @@ static void q35_host_initfn(Object *obj)
>      object_property_add_link(obj, MCH_HOST_PROP_IO_MEM, TYPE_MEMORY_REGION,
>                               (Object **) &s->mch.address_space_io,
>                               qdev_prop_allow_set_link_before_realize, 0, NULL);
> -
> -    /* Leave enough space for the biggest MCFG BAR */
> -    /* TODO: this matches current bios behaviour, but
> -     * it's not a power of two, which means an MTRR
> -     * can't cover it exactly.
> -     */
> -    range_set_bounds(&s->mch.pci_hole,
> -            MCH_HOST_BRIDGE_PCIEXBAR_DEFAULT + MCH_HOST_BRIDGE_PCIEXBAR_MAX,
> -            IO_APIC_DEFAULT_ADDRESS - 1);
>  }
>  
>  static const TypeInfo q35_host_info = {
> @@ -338,20 +329,6 @@ static void mch_update_pciexbar(MCHPCIState *mch)
>      }
>      addr = pciexbar & addr_mask;
>      pcie_host_mmcfg_update(pehb, enable, addr, length);
> -    /* Leave enough space for the MCFG BAR */
> -    /*
> -     * TODO: this matches current bios behaviour, but it's not a power of two,
> -     * which means an MTRR can't cover it exactly.
> -     */
> -    if (enable) {
> -        range_set_bounds(&mch->pci_hole,
> -                         addr + length,
> -                         IO_APIC_DEFAULT_ADDRESS - 1);
> -    } else {
> -        range_set_bounds(&mch->pci_hole,
> -                         MCH_HOST_BRIDGE_PCIEXBAR_DEFAULT,
> -                         IO_APIC_DEFAULT_ADDRESS - 1);
> -    }
>  }
>  
>  /* PAM */
> @@ -484,6 +461,14 @@ static void mch_update(MCHPCIState *mch)
>      mch_update_pam(mch);
>      mch_update_smram(mch);
>      mch_update_ext_tseg_mbytes(mch);
> +
> +    /*
> +     * pci hole goes from end-of-low-ram to io-apic.
> +     * mmconfig will be excluded by the dsdt builder.
> +     */
> +    range_set_bounds(&mch->pci_hole,
> +                     mch->below_4g_mem_size,
> +                     IO_APIC_DEFAULT_ADDRESS - 1);
>  }
>  
>  static int mch_post_load(void *opaque, int version_id)