void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
pmd_t orig = *pmdp;
*pmdp = pmd;
if (mm == &init_mm)
return;
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
/*
* Note that this routine only sets pmds for THP pages.
* Hugetlb pages are handled elsewhere. We need to check
* for huge zero page. Huge zero pages are like hugetlb
* pages in that there is no RSS, but there is the need
* for TSB entries. So, huge zero page counts go into
* hugetlb_pte_count.
*/
if (pmd_val(pmd) & _PAGE_PMD_HUGE) {
if (is_huge_zero_page(pmd_page(pmd)))
mm->context.hugetlb_pte_count++;
else
mm->context.thp_pte_count++;
} else {
if (is_huge_zero_page(pmd_page(orig)))
mm->context.hugetlb_pte_count--;
else
mm->context.thp_pte_count--;
}
/* Do not try to allocate the TSB hash table if we
* don't have one already. We have various locks held
* and thus we'll end up doing a GFP_KERNEL allocation
* in an atomic context.
*
* Instead, we let the first TLB miss on a hugepage
* take care of this.
*/
}
if (!pmd_none(orig)) {
addr &= HPAGE_MASK;
if (pmd_trans_huge(orig)) {
pte_t orig_pte = __pte(pmd_val(orig));
bool exec = pte_exec(orig_pte);
tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT);
tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
REAL_HPAGE_SHIFT);
} else {
tlb_batch_pmd_scan(mm, addr, orig);
}
}
}
/*
* This routine is only called when splitting a THP
*/
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t entry = *pmdp;
pmd_val(entry) &= ~_PAGE_VALID;
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
/*
* set_pmd_at() will not be called in a way to decrement
* thp_pte_count when splitting a THP, so do it now.
* Sanity check pmd before doing the actual decrement.
*/
if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
!is_huge_zero_page(pmd_page(entry)))
(vma->vm_mm)->context.thp_pte_count--;
}
/**
* release_pages - batched put_page()
* @pages: array of pages to release
* @nr: number of pages
*
* Decrement the reference count on all the pages in @pages. If it
* fell to zero, remove the page from the LRU and free it.
*/
void release_pages(struct page **pages, int nr)
{
int i;
LIST_HEAD(pages_to_free);
struct pglist_data *locked_pgdat = NULL;
struct lruvec *lruvec;
unsigned long uninitialized_var(flags);
unsigned int uninitialized_var(lock_batch);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
/*
* Make sure the IRQ-safe lock-holding time does not get
* excessive with a continuous string of pages from the
* same pgdat. The lock is held only if pgdat != NULL.
*/
if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) {
spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
locked_pgdat = NULL;
}
if (is_huge_zero_page(page))
continue;
/* Device public page can not be huge page */
if (is_device_public_page(page)) {
if (locked_pgdat) {
spin_unlock_irqrestore(&locked_pgdat->lru_lock,
flags);
locked_pgdat = NULL;
}
put_devmap_managed_page(page);
continue;
}
page = compound_head(page);
if (!put_page_testzero(page))
continue;
if (PageCompound(page)) {
if (locked_pgdat) {
spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
locked_pgdat = NULL;
}
__put_compound_page(page);
continue;
}
if (PageLRU(page)) {
struct pglist_data *pgdat = page_pgdat(page);
if (pgdat != locked_pgdat) {
if (locked_pgdat)
spin_unlock_irqrestore(&locked_pgdat->lru_lock,
flags);
lock_batch = 0;
locked_pgdat = pgdat;
spin_lock_irqsave(&locked_pgdat->lru_lock, flags);
}
lruvec = mem_cgroup_page_lruvec(page, locked_pgdat);
VM_BUG_ON_PAGE(!PageLRU(page), page);
__ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_off_lru(page));
}
/* Clear Active bit in case of parallel mark_page_accessed */
__ClearPageActive(page);
__ClearPageWaiters(page);
list_add(&page->lru, &pages_to_free);
}
if (locked_pgdat)
spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
mem_cgroup_uncharge_list(&pages_to_free);
free_unref_page_list(&pages_to_free);
}
/*
* Perform a free_page(), also freeing any swap cache associated with
* this page if it is the last user of the page.
*/
void free_page_and_swap_cache(struct page *page)
{
free_swap_cache(page);
if (!is_huge_zero_page(page))
put_page(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;
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;
}
u64 stable_page_flags(struct page *page)
{
u64 k;
u64 u;
/*
* pseudo flag: KPF_NOPAGE
* it differentiates a memory hole from a page with no flags
*/
if (!page)
return 1 << KPF_NOPAGE;
k = page->flags;
u = 0;
/*
* pseudo flags for the well known (anonymous) memory mapped pages
*
* Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
* simple test in page_mapcount() is not enough.
*/
if (!PageSlab(page) && page_mapcount(page))
u |= 1 << KPF_MMAP;
if (PageAnon(page))
u |= 1 << KPF_ANON;
if (PageKsm(page))
u |= 1 << KPF_KSM;
/*
* compound pages: export both head/tail info
* they together define a compound page's start/end pos and order
*/
if (PageHead(page))
u |= 1 << KPF_COMPOUND_HEAD;
if (PageTail(page))
u |= 1 << KPF_COMPOUND_TAIL;
if (PageHuge(page))
u |= 1 << KPF_HUGE;
/*
* PageTransCompound can be true for non-huge compound pages (slab
* pages or pages allocated by drivers with __GFP_COMP) because it
* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
* to make sure a given page is a thp, not a non-huge compound page.
*/
else if (PageTransCompound(page)) {
struct page *head = compound_head(page);
if (PageLRU(head) || PageAnon(head))
u |= 1 << KPF_THP;
else if (is_huge_zero_page(head)) {
u |= 1 << KPF_ZERO_PAGE;
u |= 1 << KPF_THP;
}
} else if (is_zero_pfn(page_to_pfn(page)))
u |= 1 << KPF_ZERO_PAGE;
/*
* Caveats on high order pages: page->_count will only be set
* -1 on the head page; SLUB/SLQB do the same for PG_slab;
* SLOB won't set PG_slab at all on compound pages.
*/
if (PageBuddy(page))
u |= 1 << KPF_BUDDY;
if (PageBalloon(page))
u |= 1 << KPF_BALLOON;
if (page_is_idle(page))
u |= 1 << KPF_IDLE;
u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
u |= kpf_copy_bit(k, KPF_SLAB, PG_slab);
u |= kpf_copy_bit(k, KPF_ERROR, PG_error);
u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty);
u |= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate);
u |= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback);
u |= kpf_copy_bit(k, KPF_LRU, PG_lru);
u |= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced);
u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
u |= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache);
u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked);
u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable);
u |= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked);
#ifdef CONFIG_MEMORY_FAILURE
u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
u |= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached);
#endif
u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved);
u |= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk);
u |= kpf_copy_bit(k, KPF_PRIVATE, PG_private);
u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2);
u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1);
u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1);
return u;
};
