On Fri, Feb 22, 2019 at 12:28:36PM +0100, Cédric Le Goater wrote:
> Each thread has an associated Thread Interrupt Management context
> composed of a set of registers. These registers let the thread handle
> priority management and interrupt acknowledgment. The most important
> are :
> 
>     - Interrupt Pending Buffer     (IPB)
>     - Current Processor Priority   (CPPR)
>     - Notification Source Register (NSR)
> 
> They are exposed to software in four different pages each proposing a
> view with a different privilege. The first page is for the physical
> thread context and the second for the hypervisor. Only the third
> (operating system) and the fourth (user level) are exposed the guest.
> 
> A custom VM fault handler will populate the VMA with the appropriate
> pages, which should only be the OS page for now.
> 
> Signed-off-by: Cédric Le Goater <clg@kaod.org>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

Subject to possible modification depending on whether we go with the
generic change to allow mmap() on kvm devices.

> ---
>  arch/powerpc/include/asm/xive.h            |  1 +
>  arch/powerpc/include/uapi/asm/kvm.h        |  2 ++
>  arch/powerpc/kvm/book3s_xive_native.c      | 39 ++++++++++++++++++++++
>  arch/powerpc/sysdev/xive/native.c          | 11 ++++++
>  Documentation/virtual/kvm/devices/xive.txt | 23 +++++++++++++
>  5 files changed, 76 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
> index 46891f321606..eb6d302082da 100644
> --- a/arch/powerpc/include/asm/xive.h
> +++ b/arch/powerpc/include/asm/xive.h
> @@ -23,6 +23,7 @@
>   * same offset regardless of where the code is executing
>   */
>  extern void __iomem *xive_tima;
> +extern unsigned long xive_tima_os;
>  
>  /*
>   * Offset in the TM area of our current execution level (provided by
> diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
> index 42d4ef93ec2d..be9b255e061d 100644
> --- a/arch/powerpc/include/uapi/asm/kvm.h
> +++ b/arch/powerpc/include/uapi/asm/kvm.h
> @@ -720,4 +720,6 @@ struct kvm_ppc_xive_eq {
>  #define KVM_XIVE_EQ_FLAG_ALWAYS_NOTIFY	0x00000002
>  #define KVM_XIVE_EQ_FLAG_ESCALATE	0x00000004
>  
> +#define KVM_XIVE_TIMA_PAGE_OFFSET	0
> +
>  #endif /* __LINUX_KVM_POWERPC_H */
> diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
> index 132bff52d70a..c6ac818a13b2 100644
> --- a/arch/powerpc/kvm/book3s_xive_native.c
> +++ b/arch/powerpc/kvm/book3s_xive_native.c
> @@ -176,6 +176,44 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
>  	return rc;
>  }
>  
> +static int xive_native_tima_fault(struct vm_fault *vmf)
> +{
> +	struct vm_area_struct *vma = vmf->vma;
> +
> +	switch (vmf->pgoff - vma->vm_pgoff) {
> +	case 0: /* HW - forbid access */
> +	case 1: /* HV - forbid access */
> +		return VM_FAULT_SIGBUS;
> +	case 2: /* OS */
> +		vmf_insert_pfn(vma, vmf->address, xive_tima_os >> PAGE_SHIFT);
> +		return VM_FAULT_NOPAGE;
> +	case 3: /* USER - TODO */
> +	default:
> +		return VM_FAULT_SIGBUS;
> +	}
> +}
> +
> +static const struct vm_operations_struct xive_native_tima_vmops = {
> +	.fault = xive_native_tima_fault,
> +};
> +
> +static int kvmppc_xive_native_mmap(struct kvm_device *dev,
> +				   struct vm_area_struct *vma)
> +{
> +	/* We only allow mappings at fixed offset for now */
> +	if (vma->vm_pgoff == KVM_XIVE_TIMA_PAGE_OFFSET) {
> +		if (vma_pages(vma) > 4)
> +			return -EINVAL;
> +		vma->vm_ops = &xive_native_tima_vmops;
> +	} else {
> +		return -EINVAL;
> +	}
> +
> +	vma->vm_flags |= VM_IO | VM_PFNMAP;
> +	vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
> +	return 0;
> +}
> +
>  static int kvmppc_xive_native_set_source(struct kvmppc_xive *xive, long irq,
>  					 u64 addr)
>  {
> @@ -1005,6 +1043,7 @@ struct kvm_device_ops kvm_xive_native_ops = {
>  	.set_attr = kvmppc_xive_native_set_attr,
>  	.get_attr = kvmppc_xive_native_get_attr,
>  	.has_attr = kvmppc_xive_native_has_attr,
> +	.mmap = kvmppc_xive_native_mmap,
>  };
>  
>  void kvmppc_xive_native_init_module(void)
> diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
> index 0c037e933e55..7782201e5fe8 100644
> --- a/arch/powerpc/sysdev/xive/native.c
> +++ b/arch/powerpc/sysdev/xive/native.c
> @@ -521,6 +521,9 @@ u32 xive_native_default_eq_shift(void)
>  }
>  EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
>  
> +unsigned long xive_tima_os;
> +EXPORT_SYMBOL_GPL(xive_tima_os);
> +
>  bool __init xive_native_init(void)
>  {
>  	struct device_node *np;
> @@ -573,6 +576,14 @@ bool __init xive_native_init(void)
>  	for_each_possible_cpu(cpu)
>  		kvmppc_set_xive_tima(cpu, r.start, tima);
>  
> +	/* Resource 2 is OS window */
> +	if (of_address_to_resource(np, 2, &r)) {
> +		pr_err("Failed to get thread mgmnt area resource\n");
> +		return false;
> +	}
> +
> +	xive_tima_os = r.start;
> +
>  	/* Grab size of provisionning pages */
>  	xive_parse_provisioning(np);
>  
> diff --git a/Documentation/virtual/kvm/devices/xive.txt b/Documentation/virtual/kvm/devices/xive.txt
> index 1b8957c50c53..4d6b41609fd9 100644
> --- a/Documentation/virtual/kvm/devices/xive.txt
> +++ b/Documentation/virtual/kvm/devices/xive.txt
> @@ -13,6 +13,29 @@ requires a POWER9 host and the guest OS should have support for the
>  XIVE native exploitation interrupt mode. If not, it should run using
>  the legacy interrupt mode, referred as XICS (POWER7/8).
>  
> +* Device Mappings
> +
> +  The KVM device exposes different MMIO ranges of the XIVE HW which
> +  are required for interrupt management. These are exposed to the
> +  guest in VMAs populated with a custom VM fault handler.
> +
> +  1. Thread Interrupt Management Area (TIMA)
> +
> +  Each thread has an associated Thread Interrupt Management context
> +  composed of a set of registers. These registers let the thread
> +  handle priority management and interrupt acknowledgment. The most
> +  important are :
> +
> +      - Interrupt Pending Buffer     (IPB)
> +      - Current Processor Priority   (CPPR)
> +      - Notification Source Register (NSR)
> +
> +  They are exposed to software in four different pages each proposing
> +  a view with a different privilege. The first page is for the
> +  physical thread context and the second for the hypervisor. Only the
> +  third (operating system) and the fourth (user level) are exposed the
> +  guest.
> +
>  * Groups:
>  
>    1. KVM_DEV_XIVE_GRP_CTRL

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson