Re: [PATCH v9 5/8] KVM: arm64: Support PUD hugepage in stage2_is_exec()

[Christoffer Dall]

On Wed, Oct 31, 2018 at 05:57:42PM +0000, Punit Agrawal wrote:
> In preparation for creating PUD hugepages at stage 2, add support for
> detecting execute permissions on PUD page table entries. Faults due to
> lack of execute permissions on page table entries is used to perform
> i-cache invalidation on first execute.
> 
> Provide trivial implementations of arm32 helpers to allow sharing of
> code.
> 
> Signed-off-by: Punit Agrawal <punit.agrawal@xxxxxxx>
> Reviewed-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
> Cc: Christoffer Dall <christoffer.dall@xxxxxxx>
> Cc: Marc Zyngier <marc.zyngier@xxxxxxx>
> Cc: Russell King <linux@xxxxxxxxxxxxxxx>
> Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
> Cc: Will Deacon <will.deacon@xxxxxxx>
> ---
>  arch/arm/include/asm/kvm_mmu.h         |  6 +++
>  arch/arm64/include/asm/kvm_mmu.h       |  5 +++
>  arch/arm64/include/asm/pgtable-hwdef.h |  2 +
>  virt/kvm/arm/mmu.c                     | 53 +++++++++++++++++++++++---
>  4 files changed, 61 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
> index 37bf85d39607..839a619873d3 100644
> --- a/arch/arm/include/asm/kvm_mmu.h
> +++ b/arch/arm/include/asm/kvm_mmu.h
> @@ -102,6 +102,12 @@ static inline bool kvm_s2pud_readonly(pud_t *pud)
>  	return false;
>  }
>  
> +static inline bool kvm_s2pud_exec(pud_t *pud)
> +{
> +	BUG();

nit: I think this should be WARN() now :)

> +	return false;
> +}
> +
>  static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
>  {
>  	pte_val(pte) |= L_PTE_S2_RDWR;
> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
> index 8da6d1b2a196..c755b37b3f92 100644
> --- a/arch/arm64/include/asm/kvm_mmu.h
> +++ b/arch/arm64/include/asm/kvm_mmu.h
> @@ -261,6 +261,11 @@ static inline bool kvm_s2pud_readonly(pud_t *pudp)
>  	return kvm_s2pte_readonly((pte_t *)pudp);
>  }
>  
> +static inline bool kvm_s2pud_exec(pud_t *pudp)
> +{
> +	return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
> +}
> +
>  #define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
>  
>  #ifdef __PAGETABLE_PMD_FOLDED
> diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
> index 1d7d8da2ef9b..336e24cddc87 100644
> --- a/arch/arm64/include/asm/pgtable-hwdef.h
> +++ b/arch/arm64/include/asm/pgtable-hwdef.h
> @@ -193,6 +193,8 @@
>  #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
>  #define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
>  
> +#define PUD_S2_XN		(_AT(pudval_t, 2) << 53)  /* XN[1:0] */
> +
>  /*
>   * Memory Attribute override for Stage-2 (MemAttr[3:0])
>   */
> diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
> index 1c669c3c1208..8e44dccd1b47 100644
> --- a/virt/kvm/arm/mmu.c
> +++ b/virt/kvm/arm/mmu.c
> @@ -1083,23 +1083,66 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
>  	return 0;
>  }
>  
> -static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
> +/*
> + * stage2_get_leaf_entry - walk the stage2 VM page tables and return
> + * true if a valid and present leaf-entry is found. A pointer to the
> + * leaf-entry is returned in the appropriate level variable - pudpp,
> + * pmdpp, ptepp.
> + */
> +static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
> +				  pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp)

Do we need this type madness or could this just return a u64 pointer
(NULL if nothing is found) and pass that to kvm_s2pte_exec (because we
know it's the same bit we need to check regardless of the pgtable level
on both arm and arm64)?

Or do we consider that bad for some reason?


Thanks,

    Christoffer

>  {
> +	pud_t *pudp;
>  	pmd_t *pmdp;
>  	pte_t *ptep;
>  
> -	pmdp = stage2_get_pmd(kvm, NULL, addr);
> +	*pudpp = NULL;
> +	*pmdpp = NULL;
> +	*ptepp = NULL;
> +
> +	pudp = stage2_get_pud(kvm, NULL, addr);
> +	if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp))
> +		return false;
> +
> +	if (stage2_pud_huge(kvm, *pudp)) {
> +		*pudpp = pudp;
> +		return true;
> +	}
> +
> +	pmdp = stage2_pmd_offset(kvm, pudp, addr);
>  	if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp))
>  		return false;
>  
> -	if (pmd_thp_or_huge(*pmdp))
> -		return kvm_s2pmd_exec(pmdp);
> +	if (pmd_thp_or_huge(*pmdp)) {
> +		*pmdpp = pmdp;
> +		return true;
> +	}
>  
>  	ptep = pte_offset_kernel(pmdp, addr);
>  	if (!ptep || pte_none(*ptep) || !pte_present(*ptep))
>  		return false;
>  
> -	return kvm_s2pte_exec(ptep);
> +	*ptepp = ptep;
> +	return true;
> +}
> +
> +static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
> +{
> +	pud_t *pudp;
> +	pmd_t *pmdp;
> +	pte_t *ptep;
> +	bool found;
> +
> +	found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep);
> +	if (!found)
> +		return false;
> +
> +	if (pudp)
> +		return kvm_s2pud_exec(pudp);
> +	else if (pmdp)
> +		return kvm_s2pmd_exec(pmdp);
> +	else
> +		return kvm_s2pte_exec(ptep);
>  }
>  
>  static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
> -- 
> 2.19.1
>