static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
pudp = pud_offset(&pgd, addr);
do {
pud_t pud = READ_ONCE(*pudp);
next = pud_addr_end(addr, end);
if (pud_none(pud))
return 0;
if (pud_huge(pud)) {
if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next,
write, pages, nr))
return 0;
} else if (is_hugepd(pudp)) {
if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT,
addr, next, write, pages, nr))
return 0;
} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
return 1;
}
static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
phys_addr_t addr, phys_addr_t end)
{
phys_addr_t next, start_addr = addr;
pud_t *pud, *start_pud;
start_pud = pud = pud_offset(pgd, addr);
do {
next = kvm_pud_addr_end(addr, end);
if (!pud_none(*pud)) {
if (pud_huge(*pud)) {
pud_t old_pud = *pud;
pud_clear(pud);
kvm_tlb_flush_vmid_ipa(kvm, addr);
kvm_flush_dcache_pud(old_pud);
put_page(virt_to_page(pud));
} else {
unmap_pmds(kvm, pud, addr, next);
}
}
} while (pud++, addr = next, addr != end);
if (kvm_pud_table_empty(kvm, start_pud))
clear_pgd_entry(kvm, pgd, start_addr);
}
static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
{
pmd_t *pmd_table = pmd_offset(pud, 0);
VM_BUG_ON(pud_huge(*pud));
pud_clear(pud);
kvm_tlb_flush_vmid_ipa(kvm, addr);
pmd_free(NULL, pmd_table);
put_page(virt_to_page(pud));
}
static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
unsigned long long start, u64 size)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long long addr = start, end = start + size;
u64 next;
while (addr < end) {
pgd = pgdp + pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
addr = kvm_pud_addr_end(addr, end);
continue;
}
if (pud_huge(*pud)) {
/*
* If we are dealing with a huge pud, just clear it and
* move on.
*/
clear_pud_entry(kvm, pud, addr);
addr = kvm_pud_addr_end(addr, end);
continue;
}
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
addr = kvm_pmd_addr_end(addr, end);
continue;
}
if (!kvm_pmd_huge(*pmd)) {
pte = pte_offset_kernel(pmd, addr);
clear_pte_entry(kvm, pte, addr);
next = addr + PAGE_SIZE;
}
/*
* If the pmd entry is to be cleared, walk back up the ladder
*/
if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
clear_pmd_entry(kvm, pmd, addr);
next = kvm_pmd_addr_end(addr, end);
if (page_empty(pmd) && !page_empty(pud)) {
clear_pud_entry(kvm, pud, addr);
next = kvm_pud_addr_end(addr, end);
}
}
addr = next;
}
}
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
#ifdef CONFIG_HUGETLB_SUPER_PAGES
pte_t *pte;
#endif
/* Get the top-level page table entry. */
pgd = (pgd_t *)get_pte((pte_t *)mm->pgd, pgd_index(addr), 0);
/* We don't have four levels. */
pud = pud_offset(pgd, addr);
#ifndef __PAGETABLE_PUD_FOLDED
# error support fourth page table level
#endif
if (!pud_present(*pud))
return NULL;
/* Check for an L0 huge PTE, if we have three levels. */
#ifndef __PAGETABLE_PMD_FOLDED
if (pud_huge(*pud))
return (pte_t *)pud;
pmd = (pmd_t *)get_pte((pte_t *)pud_page_vaddr(*pud),
pmd_index(addr), 1);
if (!pmd_present(*pmd))
return NULL;
#else
pmd = pmd_offset(pud, addr);
#endif
/* Check for an L1 huge PTE. */
if (pmd_huge(*pmd))
return (pte_t *)pmd;
#ifdef CONFIG_HUGETLB_SUPER_PAGES
/* Check for an L2 huge PTE. */
pte = get_pte((pte_t *)pmd_page_vaddr(*pmd), pte_index(addr), 2);
if (!pte_present(*pte))
return NULL;
if (pte_super(*pte))
return pte;
#endif
return NULL;
}
static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
phys_addr_t addr, phys_addr_t end)
{
pud_t *pud;
phys_addr_t next;
pud = pud_offset(pgd, addr);
do {
next = kvm_pud_addr_end(addr, end);
if (!pud_none(*pud)) {
if (pud_huge(*pud))
kvm_flush_dcache_pud(*pud);
else
stage2_flush_pmds(kvm, pud, addr, next);
}
} while (pud++, addr = next, addr != end);
}
void radix__change_memory_range(unsigned long start, unsigned long end,
unsigned long clear)
{
unsigned long idx;
pgd_t *pgdp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
start = ALIGN_DOWN(start, PAGE_SIZE);
end = PAGE_ALIGN(end); // aligns up
pr_debug("Changing flags on range %lx-%lx removing 0x%lx\n",
start, end, clear);
for (idx = start; idx < end; idx += PAGE_SIZE) {
pgdp = pgd_offset_k(idx);
pudp = pud_alloc(&init_mm, pgdp, idx);
if (!pudp)
continue;
if (pud_huge(*pudp)) {
ptep = (pte_t *)pudp;
goto update_the_pte;
}
pmdp = pmd_alloc(&init_mm, pudp, idx);
if (!pmdp)
continue;
if (pmd_huge(*pmdp)) {
ptep = pmdp_ptep(pmdp);
goto update_the_pte;
}
ptep = pte_alloc_kernel(pmdp, idx);
if (!ptep)
continue;
update_the_pte:
radix__pte_update(&init_mm, idx, ptep, clear, 0, 0);
}
radix__flush_tlb_kernel_range(start, end);
}
pte_t *huge_pte_offset(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
pgd_t *pgdp;
pud_t *pudp, pud;
pmd_t *pmdp, pmd;
pgdp = pgd_offset(mm, addr);
if (!pgd_present(READ_ONCE(*pgdp)))
return NULL;
pudp = pud_offset(pgdp, addr);
pud = READ_ONCE(*pudp);
if (sz != PUD_SIZE && pud_none(pud))
return NULL;
/* hugepage or swap? */
if (pud_huge(pud) || !pud_present(pud))
return (pte_t *)pudp;
/* table; check the next level */
if (sz == CONT_PMD_SIZE)
addr &= CONT_PMD_MASK;
pmdp = pmd_offset(pudp, addr);
pmd = READ_ONCE(*pmdp);
if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
pmd_none(pmd))
return NULL;
if (pmd_huge(pmd) || !pmd_present(pmd))
return (pte_t *)pmdp;
if (sz == CONT_PTE_SIZE)
return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK));
return NULL;
}
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;
}
struct page *pud_page(pud_t pud)
{
if (pud_huge(pud))
return pte_page(pud_pte(pud));
return virt_to_page(pud_page_vaddr(pud));
}
/**
* follow_page_mask - look up a page descriptor from a user-virtual address
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
* @page_mask: on output, *page_mask is set according to the size of the page
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
* Returns the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
unsigned int *page_mask)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
*page_mask = 0;
page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
if (!IS_ERR(page)) {
BUG_ON(flags & FOLL_GET);
return page;
}
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return no_page_table(vma, flags);
p4d = p4d_offset(pgd, address);
if (p4d_none(*p4d))
return no_page_table(vma, flags);
BUILD_BUG_ON(p4d_huge(*p4d));
if (unlikely(p4d_bad(*p4d)))
return no_page_table(vma, flags);
pud = pud_offset(p4d, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pud(mm, address, pud, flags);
if (page)
return page;
return no_page_table(vma, flags);
}
if (pud_devmap(*pud)) {
ptl = pud_lock(mm, pud);
page = follow_devmap_pud(vma, address, pud, flags);
spin_unlock(ptl);
if (page)
return page;
}
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pmd(mm, address, pmd, flags);
if (page)
return page;
return no_page_table(vma, flags);
}
if (pmd_devmap(*pmd)) {
ptl = pmd_lock(mm, pmd);
page = follow_devmap_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
if (page)
return page;
}
if (likely(!pmd_trans_huge(*pmd)))
return follow_page_pte(vma, address, pmd, flags);
if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
return no_page_table(vma, flags);
ptl = pmd_lock(mm, pmd);
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
return follow_page_pte(vma, address, pmd, flags);
}
if (flags & FOLL_SPLIT) {
int ret;
page = pmd_page(*pmd);
if (is_huge_zero_page(page)) {
spin_unlock(ptl);
ret = 0;
split_huge_pmd(vma, pmd, address);
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
} else {
get_page(page);
spin_unlock(ptl);
lock_page(page);
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
}
return ret ? ERR_PTR(ret) :
follow_page_pte(vma, address, pmd, flags);
}
page = follow_trans_huge_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
*page_mask = HPAGE_PMD_NR - 1;
return page;
}
/**
* follow_page_mask - look up a page descriptor from a user-virtual address
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
* @page_mask: on output, *page_mask is set according to the size of the page
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
* Returns the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
unsigned int *page_mask)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
*page_mask = 0;
page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
if (!IS_ERR(page)) {
BUG_ON(flags & FOLL_GET);
return page;
}
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return no_page_table(vma, flags);
pud = pud_offset(pgd, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
if (flags & FOLL_GET)
return NULL;
page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
return page;
}
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
if (flags & FOLL_GET) {
/*
* Refcount on tail pages are not well-defined and
* shouldn't be taken. The caller should handle a NULL
* return when trying to follow tail pages.
*/
if (PageHead(page))
get_page(page);
else
page = NULL;
}
return page;
}
if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
return no_page_table(vma, flags);
if (pmd_trans_huge(*pmd)) {
if (flags & FOLL_SPLIT) {
split_huge_page_pmd(vma, address, pmd);
return follow_page_pte(vma, address, pmd, flags);
}
ptl = pmd_lock(mm, pmd);
if (likely(pmd_trans_huge(*pmd))) {
if (unlikely(pmd_trans_splitting(*pmd))) {
spin_unlock(ptl);
wait_split_huge_page(vma->anon_vma, pmd);
} else {
page = follow_trans_huge_pmd(vma, address,
pmd, flags);
spin_unlock(ptl);
*page_mask = HPAGE_PMD_NR - 1;
return page;
}
} else
spin_unlock(ptl);
}
return follow_page_pte(vma, address, pmd, flags);
}
/**
* follow_page_mask - look up a page descriptor from a user-virtual address
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
* @page_mask: on output, *page_mask is set according to the size of the page
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
* Returns the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
unsigned int *page_mask)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
*page_mask = 0;
page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
if (!IS_ERR(page)) {
BUG_ON(flags & FOLL_GET);
return page;
}
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return no_page_table(vma, flags);
pud = pud_offset(pgd, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pud(mm, address, pud, flags);
if (page)
return page;
return no_page_table(vma, flags);
}
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
return no_page_table(vma, flags);
if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
page = follow_huge_pmd(mm, address, pmd, flags);
if (page)
return page;
return no_page_table(vma, flags);
}
if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
return no_page_table(vma, flags);
if (pmd_trans_huge(*pmd)) {
if (flags & FOLL_SPLIT) {
split_huge_page_pmd(vma, address, pmd);
return follow_page_pte(vma, address, pmd, flags);
}
ptl = pmd_lock(mm, pmd);
if (likely(pmd_trans_huge(*pmd))) {
if (unlikely(pmd_trans_splitting(*pmd))) {
spin_unlock(ptl);
wait_split_huge_page(vma->anon_vma, pmd);
} else {
page = follow_trans_huge_pmd(vma, address,
pmd, flags);
spin_unlock(ptl);
*page_mask = HPAGE_PMD_NR - 1;
return page;
}
} else
spin_unlock(ptl);
}
return follow_page_pte(vma, address, pmd, flags);
}
