On Wed, 2024-03-13 at 11:30 +0000, Christophe Leroy wrote:
>
>
> Le 13/03/2024 à 05:21, Rohan McLure a écrit :
> > In the new set_ptes() API, set_pte_at() (a special case of
> > set_ptes())
> > is intended to be instrumented by the page table check facility.
> > There
> > are however several other routines that constitute the API for
> > setting
> > page table entries, including set_pmd_at() among others. Such
> > routines
> > are themselves implemented in terms of set_ptes_at().
> >
> > A future patch providing support for page table checking on powerpc
> > must take care to avoid duplicate calls to
> > page_table_check_p{te,md,ud}_set(). Allow for assignment of pte
> > entries
> > without instrumentation through the set_pte_at_unchecked() routine
> > introduced in this patch.
> >
> > Cause API-facing routines that call set_pte_at() to instead call
> > set_pte_at_unchecked(), which will remain uninstrumented by page
> > table check. set_ptes() is itself implemented by calls to
> > __set_pte_at(), so this eliminates redundant code.
> >
> > Also prefer set_pte_at_unchecked() in early-boot usages which
> > should not be
> > instrumented.
> >
> > Signed-off-by: Rohan McLure <rmclure@xxxxxxxxxxxxx>
> > ---
> > v9: New patch
> > v10: don't reuse __set_pte_at(), as that will not apply filters.
> > Instead
> > use new set_pte_at_unchecked().
>
> Are filters needed at all in those usecases ?
I'm just retaining the original semantics of these calls. I think
another patch can replace this call with __set_pte_at() if filters are
deemed unnecessary.
>
> > ---
> > arch/powerpc/include/asm/pgtable.h | 2 ++
> > arch/powerpc/mm/book3s64/hash_pgtable.c | 2 +-
> > arch/powerpc/mm/book3s64/pgtable.c | 6 +++---
> > arch/powerpc/mm/book3s64/radix_pgtable.c | 8 ++++----
> > arch/powerpc/mm/nohash/book3e_pgtable.c | 2 +-
> > arch/powerpc/mm/pgtable.c | 7 +++++++
> > arch/powerpc/mm/pgtable_32.c | 2 +-
> > 7 files changed, 19 insertions(+), 10 deletions(-)
> >
> > diff --git a/arch/powerpc/include/asm/pgtable.h
> > b/arch/powerpc/include/asm/pgtable.h
> > index 3741a63fb82e..6ff1d8cfa216 100644
> > --- a/arch/powerpc/include/asm/pgtable.h
> > +++ b/arch/powerpc/include/asm/pgtable.h
> > @@ -44,6 +44,8 @@ struct mm_struct;
> > void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t
> > *ptep,
> > pte_t pte, unsigned int nr);
> > #define set_ptes set_ptes
> > +void set_pte_at_unchecked(struct mm_struct *mm, unsigned long
> > addr,
> > + pte_t *ptep, pte_t pte);
> > #define update_mmu_cache(vma, addr, ptep) \
> > update_mmu_cache_range(NULL, vma, addr, ptep, 1)
> >
> > diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c
> > b/arch/powerpc/mm/book3s64/hash_pgtable.c
> > index 988948d69bc1..871472f99a01 100644
> > --- a/arch/powerpc/mm/book3s64/hash_pgtable.c
> > +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c
> > @@ -165,7 +165,7 @@ int hash__map_kernel_page(unsigned long ea,
> > unsigned long pa, pgprot_t prot)
> > ptep = pte_alloc_kernel(pmdp, ea);
> > if (!ptep)
> > return -ENOMEM;
> > - set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >>
> > PAGE_SHIFT, prot));
> > + set_pte_at_unchecked(&init_mm, ea, ptep,
> > pfn_pte(pa >> PAGE_SHIFT, prot));
> > } else {
> > /*
> > * If the mm subsystem is not fully up, we cannot
> > create a
> > diff --git a/arch/powerpc/mm/book3s64/pgtable.c
> > b/arch/powerpc/mm/book3s64/pgtable.c
> > index 3438ab72c346..25082ab6018b 100644
> > --- a/arch/powerpc/mm/book3s64/pgtable.c
> > +++ b/arch/powerpc/mm/book3s64/pgtable.c
> > @@ -116,7 +116,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned
> > long addr,
> > WARN_ON(!(pmd_large(pmd)));
> > #endif
> > trace_hugepage_set_pmd(addr, pmd_val(pmd));
> > - return set_pte_at(mm, addr, pmdp_ptep(pmdp),
> > pmd_pte(pmd));
> > + return set_pte_at_unchecked(mm, addr, pmdp_ptep(pmdp),
> > pmd_pte(pmd));
> > }
> >
> > void set_pud_at(struct mm_struct *mm, unsigned long addr,
> > @@ -133,7 +133,7 @@ void set_pud_at(struct mm_struct *mm, unsigned
> > long addr,
> > WARN_ON(!(pud_large(pud)));
> > #endif
> > trace_hugepage_set_pud(addr, pud_val(pud));
> > - return set_pte_at(mm, addr, pudp_ptep(pudp),
> > pud_pte(pud));
> > + return set_pte_at_unchecked(mm, addr, pudp_ptep(pudp),
> > pud_pte(pud));
> > }
> >
> > static void do_serialize(void *arg)
> > @@ -539,7 +539,7 @@ void ptep_modify_prot_commit(struct
> > vm_area_struct *vma, unsigned long addr,
> > if (radix_enabled())
> > return radix__ptep_modify_prot_commit(vma, addr,
> > ptep,
> > old_pte, pte);
> > - set_pte_at(vma->vm_mm, addr, ptep, pte);
> > + set_pte_at_unchecked(vma->vm_mm, addr, ptep, pte);
> > }
> >
> > #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> > diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c
> > b/arch/powerpc/mm/book3s64/radix_pgtable.c
> > index 46fa46ce6526..c661e42bb2f1 100644
> > --- a/arch/powerpc/mm/book3s64/radix_pgtable.c
> > +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
> > @@ -109,7 +109,7 @@ static int early_map_kernel_page(unsigned long
> > ea, unsigned long pa,
> > ptep = pte_offset_kernel(pmdp, ea);
> >
> > set_the_pte:
> > - set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
> > + set_pte_at_unchecked(&init_mm, ea, ptep, pfn_pte(pfn,
> > flags));
> > asm volatile("ptesync": : :"memory");
> > return 0;
> > }
> > @@ -1522,7 +1522,7 @@ void radix__ptep_modify_prot_commit(struct
> > vm_area_struct *vma,
> > (atomic_read(&mm->context.copros) > 0))
> > radix__flush_tlb_page(vma, addr);
> >
> > - set_pte_at(mm, addr, ptep, pte);
> > + set_pte_at_unchecked(mm, addr, ptep, pte);
> > }
> >
> > int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
> > @@ -1533,7 +1533,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t
> > addr, pgprot_t prot)
> > if (!radix_enabled())
> > return 0;
> >
> > - set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pud);
> > + set_pte_at_unchecked(&init_mm, 0 /* radix unused */, ptep,
> > new_pud);
> >
> > return 1;
> > }
> > @@ -1580,7 +1580,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t
> > addr, pgprot_t prot)
> > if (!radix_enabled())
> > return 0;
> >
> > - set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pmd);
> > + set_pte_at_unchecked(&init_mm, 0 /* radix unused */, ptep,
> > new_pmd);
> >
> > return 1;
> > }
> > diff --git a/arch/powerpc/mm/nohash/book3e_pgtable.c
> > b/arch/powerpc/mm/nohash/book3e_pgtable.c
> > index 1c5e4ecbebeb..10d487b2b991 100644
> > --- a/arch/powerpc/mm/nohash/book3e_pgtable.c
> > +++ b/arch/powerpc/mm/nohash/book3e_pgtable.c
> > @@ -111,7 +111,7 @@ int __ref map_kernel_page(unsigned long ea,
> > phys_addr_t pa, pgprot_t prot)
> > }
> > ptep = pte_offset_kernel(pmdp, ea);
> > }
> > - set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
> > prot));
> > + set_pte_at_unchecked(&init_mm, ea, ptep, pfn_pte(pa >>
> > PAGE_SHIFT, prot));
> >
> > smp_wmb();
> > return 0;
> > diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
> > index e8e0289d7ab0..352679cf2684 100644
> > --- a/arch/powerpc/mm/pgtable.c
> > +++ b/arch/powerpc/mm/pgtable.c
> > @@ -227,6 +227,13 @@ void set_ptes(struct mm_struct *mm, unsigned
> > long addr, pte_t *ptep,
> > }
> > }
> >
> > +void set_pte_at_unchecked(struct mm_struct *mm, unsigned long
> > addr,
> > + pte_t *ptep, pte_t pte)
> > +{
>
> No need of the
>
> VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
>
> which is in set_ptes() ?
Good spot, I'll include that check in this routine.
>
> > + pte = set_pte_filter(pte, addr);
> > + __set_pte_at(mm, addr, ptep, pte, 0);
> > +}
> > +
> > void unmap_kernel_page(unsigned long va)
> > {
> > pmd_t *pmdp = pmd_off_k(va);
> > diff --git a/arch/powerpc/mm/pgtable_32.c
> > b/arch/powerpc/mm/pgtable_32.c
> > index 4be97b4a44f9..a5a26faf91ec 100644
> > --- a/arch/powerpc/mm/pgtable_32.c
> > +++ b/arch/powerpc/mm/pgtable_32.c
> > @@ -89,7 +89,7 @@ int __ref map_kernel_page(unsigned long va,
> > phys_addr_t pa, pgprot_t prot)
> > * hash table
> > */
> > BUG_ON((pte_present(*pg) | pte_hashpte(*pg)) &&
> > pgprot_val(prot));
> > - set_pte_at(&init_mm, va, pg, pfn_pte(pa >>
> > PAGE_SHIFT, prot));
> > + set_pte_at_unchecked(&init_mm, va, pg, pfn_pte(pa
> > >> PAGE_SHIFT, prot));
> > }
> > smp_wmb();
> > return err;
