int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
int ncontig, i, changed = 0;
size_t pgsize = 0;
unsigned long pfn = pte_pfn(pte), dpfn;
pgprot_t hugeprot;
pte_t orig_pte;
if (!pte_cont(pte))
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
dpfn = pgsize >> PAGE_SHIFT;
orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
if (!pte_same(orig_pte, pte))
changed = 1;
/* Make sure we don't lose the dirty state */
if (pte_dirty(orig_pte))
pte = pte_mkdirty(pte);
hugeprot = pte_pgprot(pte);
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
return changed;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
unsigned long pfn, dpfn;
pgprot_t hugeprot;
int ncontig, i;
size_t pgsize;
pte_t pte;
if (!pte_cont(READ_ONCE(*ptep))) {
ptep_set_wrprotect(mm, addr, ptep);
return;
}
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
dpfn = pgsize >> PAGE_SHIFT;
pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
pte = pte_wrprotect(pte);
hugeprot = pte_pgprot(pte);
pfn = pte_pfn(pte);
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
}
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
size_t pgsize;
int i;
int ncontig;
unsigned long pfn, dpfn;
pgprot_t hugeprot;
/*
* Code needs to be expanded to handle huge swap and migration
* entries. Needed for HUGETLB and MEMORY_FAILURE.
*/
WARN_ON(!pte_present(pte));
if (!pte_cont(pte)) {
set_pte_at(mm, addr, ptep, pte);
return;
}
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
pfn = pte_pfn(pte);
dpfn = pgsize >> PAGE_SHIFT;
hugeprot = pte_pgprot(pte);
clear_flush(mm, addr, ptep, pgsize, ncontig);
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
}
static int find_num_contig(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte, size_t *pgsize)
{
pgd_t *pgd = pgd_offset(mm, addr);
pud_t *pud;
pmd_t *pmd;
*pgsize = PAGE_SIZE;
if (!pte_cont(pte))
return 1;
if (!pgd_present(*pgd)) {
VM_BUG_ON(!pgd_present(*pgd));
return 1;
}
pud = pud_offset(pgd, addr);
if (!pud_present(*pud)) {
VM_BUG_ON(!pud_present(*pud));
return 1;
}
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd)) {
VM_BUG_ON(!pmd_present(*pmd));
return 1;
}
if ((pte_t *)pmd == ptep) {
*pgsize = PMD_SIZE;
return CONT_PMDS;
}
return CONT_PTES;
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
pte_t pte;
if (pte_cont(*ptep)) {
int ncontig, i;
size_t pgsize;
pte_t *cpte;
bool is_dirty = false;
cpte = huge_pte_offset(mm, addr);
ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
/* save the 1st pte to return */
pte = ptep_get_and_clear(mm, addr, cpte);
for (i = 1; i < ncontig; ++i) {
/*
* If HW_AFDBM is enabled, then the HW could
* turn on the dirty bit for any of the page
* in the set, so check them all.
*/
++cpte;
if (pte_dirty(ptep_get_and_clear(mm, addr, cpte)))
is_dirty = true;
}
if (is_dirty)
return pte_mkdirty(pte);
else
return pte;
} else {
return ptep_get_and_clear(mm, addr, ptep);
}
}
void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
size_t pgsize;
int ncontig;
if (!pte_cont(READ_ONCE(*ptep))) {
ptep_clear_flush(vma, addr, ptep);
return;
}
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
int ncontig;
size_t pgsize;
pte_t orig_pte = huge_ptep_get(ptep);
if (!pte_cont(orig_pte))
return ptep_get_and_clear(mm, addr, ptep);
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
}
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd = NULL;
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
if (!pgd_present(*pgd))
return NULL;
pud = pud_offset(pgd, addr);
if (!pud_present(*pud))
return NULL;
if (pud_huge(*pud))
return (pte_t *)pud;
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd))
return NULL;
if (pte_cont(pmd_pte(*pmd))) {
pmd = pmd_offset(
pud, (addr & CONT_PMD_MASK));
return (pte_t *)pmd;
}
if (pmd_huge(*pmd))
return (pte_t *)pmd;
pte = pte_offset_kernel(pmd, addr);
if (pte_present(*pte) && pte_cont(*pte)) {
pte = pte_offset_kernel(
pmd, (addr & CONT_PTE_MASK));
return pte;
}
return NULL;
}
