Re: [PATCH V3 3/3] Support Xen pv-domains using PAT

[Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>]

On Fri, Sep 12, 2014 at 12:35:12PM +0200, Juergen Gross wrote:
> With the dynamical mapping between cache modes and pgprot values it is
> now possible to use all cache modes via the Xen hypervisor PAT settings
> in a pv domain.
> 
> All to be done is to read the PAT configuration MSR and set up the
> translation tables accordingly.
> 
> Signed-off-by: Juergen Gross <jgross@suse.com>
> Reviewed-by: David Vrabel <david.vrabel@citrix.com>

Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

> ---
>  arch/x86/xen/enlighten.c | 25 +++++++------------------
>  arch/x86/xen/mmu.c       | 48 ++----------------------------------------------
>  arch/x86/xen/xen-ops.h   |  1 -
>  3 files changed, 9 insertions(+), 65 deletions(-)

Oh yeah! That is nice to see :-)

> 
> diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
> index c0cb11f..75ac572 100644
> --- a/arch/x86/xen/enlighten.c
> +++ b/arch/x86/xen/enlighten.c
> @@ -1100,12 +1100,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
>  		/* Fast syscall setup is all done in hypercalls, so
>  		   these are all ignored.  Stub them out here to stop
>  		   Xen console noise. */
> -		break;
> -
> -	case MSR_IA32_CR_PAT:
> -		if (smp_processor_id() == 0)
> -			xen_set_pat(((u64)high << 32) | low);
> -		break;
>  
>  	default:
>  		ret = native_write_msr_safe(msr, low, high);
> @@ -1554,10 +1548,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
>  
>  	/* Prevent unwanted bits from being set in PTEs. */
>  	__supported_pte_mask &= ~_PAGE_GLOBAL;
> -#if 0
> -	if (!xen_initial_domain())
> -#endif
> -		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
>  
>  	__supported_pte_mask |= _PAGE_IOMAP;
>  
> @@ -1613,14 +1603,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
>  	 */
>  	acpi_numa = -1;
>  #endif
> -#ifdef CONFIG_X86_PAT
> -	/*
> -	 * For right now disable the PAT. We should remove this once
> -	 * git commit 8eaffa67b43e99ae581622c5133e20b0f48bcef1
> -	 * (xen/pat: Disable PAT support for now) is reverted.
> -	 */
> -	pat_enabled = 0;
> -#endif
>  	/* Don't do the full vcpu_info placement stuff until we have a
>  	   possible map and a non-dummy shared_info. */
>  	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
> @@ -1634,6 +1616,13 @@ asmlinkage __visible void __init xen_start_kernel(void)
>  	/* Allocate and initialize top and mid mfn levels for p2m structure */
>  	xen_build_mfn_list_list();
>  
> +	/*
> +	 * Modify the cache mode translation tables to match Xen's PAT
> +	 * configuration.
> +	 */
> +
> +	pat_init_cache_modes();
> +
>  	/* keep using Xen gdt for now; no urgent need to change it */
>  
>  #ifdef CONFIG_X86_32
> diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
> index e8a1201..70702e9 100644
> --- a/arch/x86/xen/mmu.c
> +++ b/arch/x86/xen/mmu.c
> @@ -434,13 +434,7 @@ static pteval_t iomap_pte(pteval_t val)
>  __visible pteval_t xen_pte_val(pte_t pte)
>  {
>  	pteval_t pteval = pte.pte;
> -#if 0
> -	/* If this is a WC pte, convert back from Xen WC to Linux WC */
> -	if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
> -		WARN_ON(!pat_enabled);
> -		pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
> -	}
> -#endif
> +
>  	if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
>  		return pteval;
>  
> @@ -454,48 +448,10 @@ __visible pgdval_t xen_pgd_val(pgd_t pgd)
>  }
>  PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
>  
> -/*
> - * Xen's PAT setup is part of its ABI, though I assume entries 6 & 7
> - * are reserved for now, to correspond to the Intel-reserved PAT
> - * types.
> - *
> - * We expect Linux's PAT set as follows:
> - *
> - * Idx  PTE flags        Linux    Xen    Default
> - * 0                     WB       WB     WB
> - * 1            PWT      WC       WT     WT
> - * 2        PCD          UC-      UC-    UC-
> - * 3        PCD PWT      UC       UC     UC
> - * 4    PAT              WB       WC     WB
> - * 5    PAT     PWT      WC       WP     WT
> - * 6    PAT PCD          UC-      rsv    UC-
> - * 7    PAT PCD PWT      UC       rsv    UC
> - */
> -
> -void xen_set_pat(u64 pat)
> -{
> -	/* We expect Linux to use a PAT setting of
> -	 * UC UC- WC WB (ignoring the PAT flag) */
> -	WARN_ON(pat != 0x0007010600070106ull);
> -}
> -
>  __visible pte_t xen_make_pte(pteval_t pte)
>  {
>  	phys_addr_t addr = (pte & PTE_PFN_MASK);
> -#if 0
> -	/* If Linux is trying to set a WC pte, then map to the Xen WC.
> -	 * If _PAGE_PAT is set, then it probably means it is really
> -	 * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
> -	 * things work out OK...
> -	 *
> -	 * (We should never see kernel mappings with _PAGE_PSE set,
> -	 * but we could see hugetlbfs mappings, I think.).
> -	 */
> -	if (pat_enabled && !WARN_ON(pte & _PAGE_PAT)) {
> -		if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
> -			pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
> -	}
> -#endif
> +
>  	/*
>  	 * Unprivileged domains are allowed to do IOMAPpings for
>  	 * PCI passthrough, but not map ISA space.  The ISA
> diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
> index 28c7e0b..4ab9298 100644
> --- a/arch/x86/xen/xen-ops.h
> +++ b/arch/x86/xen/xen-ops.h
> @@ -33,7 +33,6 @@ extern unsigned long xen_max_p2m_pfn;
>  
>  void xen_mm_pin_all(void);
>  void xen_mm_unpin_all(void);
> -void xen_set_pat(u64);
>  
>  char * __init xen_memory_setup(void);
>  char * xen_auto_xlated_memory_setup(void);
> -- 
> 1.8.4.5
>