Re: [PATCH] x86/hyperv: Fix the detection of E820_TYPE_PRAM in a Gen2 VM

[Wei Liu <wei.liu@kernel.org>]

On Mon, Sep 18, 2023 at 10:36:47PM -0700, Saurabh Singh Sengar wrote:
> On Thu, Aug 10, 2023 at 10:31:37PM -0700, Dexuan Cui wrote:
> > A Gen2 VM doesn't support legacy PCI/PCIe, so both raw_pci_ops and
> > raw_pci_ext_ops are NULL, and pci_subsys_init() -> pcibios_init()
> > doesn't call pcibios_resource_survey() -> e820__reserve_resources_late();
> > as a result, any emulated persistent memory of E820_TYPE_PRAM (12) via
> > the kernel parameter memmap=nn[KMG]!ss is not added into iomem_resource
> > and hence can't be detected by register_e820_pmem().
> > 
> > Fix this by directly calling e820__reserve_resources_late() in
> > hv_pci_init(), which is called from arch_initcall(pci_arch_init).
> > 
> > It's ok to move a Gen2 VM's e820__reserve_resources_late() from
> > subsys_initcall(pci_subsys_init) to arch_initcall(pci_arch_init) because
> > the code in-between doesn't depend on the E820 resources.
> > e820__reserve_resources_late() depends on e820__reserve_resources(),
> > which has been called earlier from setup_arch().
> > 
> > For a Gen-2 VM, the new hv_pci_init() also adds any memory of
> > E820_TYPE_PMEM (7) into iomem_resource, and acpi_nfit_register_region() ->
> > acpi_nfit_insert_resource() -> region_intersects() returns
> > REGION_INTERSECTS, so the memory of E820_TYPE_PMEM won't get added twice.
> > 
> > Changed the local variable "int gen2vm" to "bool gen2vm".
> > 
> > Signed-off-by: Saurabh Sengar <ssengar@linux.microsoft.com>
> > Signed-off-by: Dexuan Cui <decui@microsoft.com>
> > ---
> >  arch/x86/hyperv/hv_init.c | 25 +++++++++++++++++++++----
> >  1 file changed, 21 insertions(+), 4 deletions(-)
> > 
> > diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> > index b004370d3b01..6b22d49aee7b 100644
> > --- a/arch/x86/hyperv/hv_init.c
> > +++ b/arch/x86/hyperv/hv_init.c
> > @@ -13,6 +13,7 @@
> >  #include <linux/io.h>
> >  #include <asm/apic.h>
> >  #include <asm/desc.h>
> > +#include <asm/e820/api.h>
> >  #include <asm/sev.h>
> >  #include <asm/hypervisor.h>
> >  #include <asm/hyperv-tlfs.h>
> > @@ -282,15 +283,31 @@ static int hv_cpu_die(unsigned int cpu)
> >  
> >  static int __init hv_pci_init(void)
> >  {
> > -	int gen2vm = efi_enabled(EFI_BOOT);
> > +	bool gen2vm = efi_enabled(EFI_BOOT);
> >  
> >  	/*
> > -	 * For Generation-2 VM, we exit from pci_arch_init() by returning 0.
> > -	 * The purpose is to suppress the harmless warning:
> > +	 * A Generation-2 VM doesn't support legacy PCI/PCIe, so both
> > +	 * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() ->
> > +	 * pcibios_init() doesn't call pcibios_resource_survey() ->
> > +	 * e820__reserve_resources_late(); as a result, any emulated persistent
> > +	 * memory of E820_TYPE_PRAM (12) via the kernel parameter
> > +	 * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be
> > +	 * detected by register_e820_pmem(). Fix this by directly calling
> > +	 * e820__reserve_resources_late() here: e820__reserve_resources_late()
> > +	 * depends on e820__reserve_resources(), which has been called earlier
> > +	 * from setup_arch(). Note: e820__reserve_resources_late() also adds
> > +	 * any memory of E820_TYPE_PMEM (7) into iomem_resource, and
> > +	 * acpi_nfit_register_region() -> acpi_nfit_insert_resource() ->
> > +	 * region_intersects() returns REGION_INTERSECTS, so the memory of
> > +	 * E820_TYPE_PMEM won't get added twice.
> > +	 *
> > +	 * We return 0 here so that pci_arch_init() won't print the warning:
> >  	 * "PCI: Fatal: No config space access function found"
> >  	 */
> > -	if (gen2vm)
> > +	if (gen2vm) {
> > +		e820__reserve_resources_late();
> >  		return 0;
> > +	}
> 
> 
> Kind reminder to review this.
> 

I tried to applied this patch to hyperv-fixes, but it doesn't apply
cleanly.

Please resend.

Thanks,
Wei.