| Message ID | 20220130211838.8382-17-rick.p.edgecombe@intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Shadow stacks for userspace | expand |
First of all, that changelog doesn't really explain the problem. It's all background and no "why". *Why* does maybe_mkwrite() take a VMA? What's the point? > #endif /* _ASM_X86_PGTABLE_H */ > diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c > index 3481b35cb4ec..c22c8e9c37e8 100644 > --- a/arch/x86/mm/pgtable.c > +++ b/arch/x86/mm/pgtable.c > @@ -610,6 +610,26 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, > } > #endif > > +pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) > +{ > + if (vma->vm_flags & VM_WRITE) > + pte = pte_mkwrite(pte); > + else if (vma->vm_flags & VM_SHADOW_STACK) > + pte = pte_mkwrite_shstk(pte); > + return pte; > +} First, this makes me wonder why we need pte_mkwrite() *AND* pte_mkwrite_shstk(). Is there a difference in their behavior that matters? Second, I don't like the copy-and-paste to make an arch-specific "hook" for a function. This is a very good way to ensure that arch code and generic code fork and accumulate separate bugs. I'd much rather have this do (in generic code): pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (vma->vm_flags & VM_WRITE) pte = pte_mkwrite(pte); pte = arch_maybe_mkwrite(pte, vma); return pte; +} Actually, is there a reason the generic code could not even just add: if (vma->vm_flags & VM_ARCH_MAYBE_MKWRITE_MASK) pte = arch_maybe_mkwrite(pte, vma); or heck even just the x86-specific code itself: if (vma->vm_flags & VM_SHADOW_STACK) pte = pte_mkwrite_shstk(pte); with a stub defined for pte_mkwrite_shstk()? In the end, it's just a question of whether the generic code wants something to say "arch" or "shstk". But, I don't think we need a forked x86 copy of these functions. > diff --git a/include/linux/mm.h b/include/linux/mm.h > index 311c6018d503..b3cb3a17037b 100644 > --- a/include/linux/mm.h > +++ b/include/linux/mm.h > @@ -955,12 +955,14 @@ void free_compound_page(struct page *page); > * pte_mkwrite. But get_user_pages can cause write faults for mappings > * that do not have writing enabled, when used by access_process_vm. > */ > +#ifndef maybe_mkwrite maybe_mkwrite is defined in asm/pgtable.h. Where is the #include? > static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) > { > if (likely(vma->vm_flags & VM_WRITE)) > pte = pte_mkwrite(pte); > return pte; > } > +#endif > > vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); > void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr); > diff --git a/mm/huge_memory.c b/mm/huge_memory.c > index 406a3c28c026..2adedcfca00b 100644 > --- a/mm/huge_memory.c > +++ b/mm/huge_memory.c > @@ -491,12 +491,14 @@ static int __init setup_transparent_hugepage(char *str) > } > __setup("transparent_hugepage=", setup_transparent_hugepage); > > +#ifndef maybe_pmd_mkwrite > pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) > { > if (likely(vma->vm_flags & VM_WRITE)) > pmd = pmd_mkwrite(pmd); > return pmd; > } > +#endif > > #ifdef CONFIG_MEMCG > static inline struct deferred_split *get_deferred_split_queue(struct page *page)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e1061b9cba6a..36166bdd0b98 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -282,6 +282,9 @@ static inline int pmd_trans_huge(pmd_t pmd) return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } +#define maybe_pmd_mkwrite maybe_pmd_mkwrite +extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); + #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_trans_huge(pud_t pud) { @@ -1660,6 +1663,9 @@ static inline bool arch_faults_on_old_pte(void) return false; } +#define maybe_mkwrite maybe_mkwrite +extern pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 3481b35cb4ec..c22c8e9c37e8 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -610,6 +610,26 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, } #endif +pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_WRITE) + pte = pte_mkwrite(pte); + else if (vma->vm_flags & VM_SHADOW_STACK) + pte = pte_mkwrite_shstk(pte); + return pte; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_WRITE) + pmd = pmd_mkwrite(pmd); + else if (vma->vm_flags & VM_SHADOW_STACK) + pmd = pmd_mkwrite_shstk(pmd); + return pmd; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve diff --git a/include/linux/mm.h b/include/linux/mm.h index 311c6018d503..b3cb3a17037b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -955,12 +955,14 @@ void free_compound_page(struct page *page); * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ +#ifndef maybe_mkwrite static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte); return pte; } +#endif vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 406a3c28c026..2adedcfca00b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -491,12 +491,14 @@ static int __init setup_transparent_hugepage(char *str) } __setup("transparent_hugepage=", setup_transparent_hugepage); +#ifndef maybe_pmd_mkwrite pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pmd = pmd_mkwrite(pmd); return pmd; } +#endif #ifdef CONFIG_MEMCG static inline struct deferred_split *get_deferred_split_queue(struct page *page)