/*
* Lookup a swap entry in the swap cache. A found page will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *page;
page = find_get_page(swap_address_space(entry), swp_offset(entry));
if (page && likely(!PageTransCompound(page))) {
INC_CACHE_INFO(find_success);
if (TestClearPageReadahead(page))
atomic_inc(&swapin_readahead_hits);
}
INC_CACHE_INFO(find_total);
return page;
}
static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
{
pfn_t pfn = *pfnp;
gfn_t gfn = *ipap >> PAGE_SHIFT;
if (PageTransCompound(pfn_to_page(pfn))) {
unsigned long mask;
/*
* The address we faulted on is backed by a transparent huge
* page. However, because we map the compound huge page and
* not the individual tail page, we need to transfer the
* refcount to the head page. We have to be careful that the
* THP doesn't start to split while we are adjusting the
* refcounts.
*
* We are sure this doesn't happen, because mmu_notifier_retry
* was successful and we are holding the mmu_lock, so if this
* THP is trying to split, it will be blocked in the mmu
* notifier before touching any of the pages, specifically
* before being able to call __split_huge_page_refcount().
*
* We can therefore safely transfer the refcount from PG_tail
* to PG_head and switch the pfn from a tail page to the head
* page accordingly.
*/
mask = PTRS_PER_PMD - 1;
VM_BUG_ON((gfn & mask) != (pfn & mask));
if (pfn & mask) {
*ipap &= PMD_MASK;
kvm_release_pfn_clean(pfn);
pfn &= ~mask;
kvm_get_pfn(pfn);
*pfnp = pfn;
}
return true;
}
return false;
}
/**
* swapin_readahead - swap in pages in hope we need them soon
* @entry: swap entry of this memory
* @gfp_mask: memory allocation flags
* @vma: user vma this address belongs to
* @addr: target address for mempolicy
*
* Returns the struct page for entry and addr, after queueing swapin.
*
* Primitive swap readahead code. We simply read an aligned block of
* (1 << page_cluster) entries in the swap area. This method is chosen
* because it doesn't cost us any seek time. We also make sure to queue
* the 'original' request together with the readahead ones...
*
* This has been extended to use the NUMA policies from the mm triggering
* the readahead.
*
* Caller must hold down_read on the vma->vm_mm if vma is not NULL.
*/
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
unsigned long entry_offset = swp_offset(entry);
unsigned long offset = entry_offset;
unsigned long start_offset, end_offset;
unsigned long mask;
struct blk_plug plug;
bool do_poll = true;
mask = swapin_nr_pages(offset) - 1;
if (!mask)
goto skip;
do_poll = false;
/* Read a page_cluster sized and aligned cluster around offset. */
start_offset = offset & ~mask;
end_offset = offset | mask;
if (!start_offset) /* First page is swap header. */
start_offset++;
blk_start_plug(&plug);
for (offset = start_offset; offset <= end_offset ; offset++) {
/* Ok, do the async read-ahead now */
page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
gfp_mask, vma, addr, false);
if (!page)
continue;
if (offset != entry_offset && likely(!PageTransCompound(page)))
SetPageReadahead(page);
put_page(page);
}
blk_finish_plug(&plug);
lru_add_drain(); /* Push any new pages onto the LRU now */
skip:
return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
struct mm_struct *mm = vma->vm_mm;
struct dev_pagemap *pgmap = NULL;
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
retry:
if (unlikely(pmd_bad(*pmd)))
return no_page_table(vma, flags);
ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
pte = *ptep;
if (!pte_present(pte)) {
swp_entry_t entry;
/*
* KSM's break_ksm() relies upon recognizing a ksm page
* even while it is being migrated, so for that case we
* need migration_entry_wait().
*/
if (likely(!(flags & FOLL_MIGRATION)))
goto no_page;
if (pte_none(pte))
goto no_page;
entry = pte_to_swp_entry(pte);
if (!is_migration_entry(entry))
goto no_page;
pte_unmap_unlock(ptep, ptl);
migration_entry_wait(mm, pmd, address);
goto retry;
}
if ((flags & FOLL_NUMA) && pte_protnone(pte))
goto no_page;
if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
pte_unmap_unlock(ptep, ptl);
return NULL;
}
page = vm_normal_page(vma, address, pte);
if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
/*
* Only return device mapping pages in the FOLL_GET case since
* they are only valid while holding the pgmap reference.
*/
pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
if (pgmap)
page = pte_page(pte);
else
goto no_page;
} else if (unlikely(!page)) {
if (flags & FOLL_DUMP) {
/* Avoid special (like zero) pages in core dumps */
page = ERR_PTR(-EFAULT);
goto out;
}
if (is_zero_pfn(pte_pfn(pte))) {
page = pte_page(pte);
} else {
int ret;
ret = follow_pfn_pte(vma, address, ptep, flags);
page = ERR_PTR(ret);
goto out;
}
}
if (flags & FOLL_SPLIT && PageTransCompound(page)) {
int ret;
get_page(page);
pte_unmap_unlock(ptep, ptl);
lock_page(page);
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
if (ret)
return ERR_PTR(ret);
goto retry;
}
if (flags & FOLL_GET) {
get_page(page);
/* drop the pgmap reference now that we hold the page */
if (pgmap) {
put_dev_pagemap(pgmap);
pgmap = NULL;
}
}
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
set_page_dirty(page);
/*
* pte_mkyoung() would be more correct here, but atomic care
* is needed to avoid losing the dirty bit: it is easier to use
* mark_page_accessed().
*/
mark_page_accessed(page);
}
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/* Do not mlock pte-mapped THP */
if (PageTransCompound(page))
goto out;
/*
* The preliminary mapping check is mainly to avoid the
* pointless overhead of lock_page on the ZERO_PAGE
* which might bounce very badly if there is contention.
*
* If the page is already locked, we don't need to
* handle it now - vmscan will handle it later if and
* when it attempts to reclaim the page.
*/
if (page->mapping && trylock_page(page)) {
lru_add_drain(); /* push cached pages to LRU */
/*
* Because we lock page here, and migration is
* blocked by the pte's page reference, and we
* know the page is still mapped, we don't even
* need to check for file-cache page truncation.
*/
mlock_vma_page(page);
unlock_page(page);
}
}
out:
pte_unmap_unlock(ptep, ptl);
return page;
no_page:
pte_unmap_unlock(ptep, ptl);
if (!pte_none(pte))
return NULL;
return no_page_table(vma, flags);
}
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;
};
