/**
* Claim a given page from the buddy subsystem. This only works, if the page registered within the buddy system and marked as free
*
*/
int
try_claim_free_buddy_page(struct page* requested_page,
unsigned int allowed_sources, struct page** allocated_page,
unsigned long* actual_source) {
int ret = CLAIMED_TRY_NEXT;
if (allowed_sources & SOURCE_FREE_BUDDY_PAGE) {
struct page * locked_page = NULL;
unsigned long pfn = page_to_pfn(requested_page);
unsigned int locked_page_count_after, locked_page_count_before;
/*
* Isolate the page, so that it doesn't get reallocated if it
* was free.
*/
set_migratetype_isolate(requested_page);
locked_page_count_before = page_count(requested_page);
if (0 == page_count(compound_head(requested_page))) {
if (is_free_buddy_page(requested_page)) {
printk(KERN_DEBUG "try_claim_free_buddy_page: %#lx free buddy page\n", pfn);
/* get, while page is still isolated */
locked_page = claim_free_buddy_page(requested_page);
} else {
printk(KERN_DEBUG
"try_claim_free_buddy_page: %#lx: unknown zero refcount page type %lx\n",
pfn, requested_page->flags);
}
} else {
long cppfn = page_to_pfn(compound_head(requested_page));
/* Not a free page */
printk(KERN_DEBUG
"try_claim_free_buddy_page: %#lx: %#lx refcount %i ,page type %lx\n",
pfn, cppfn, page_count(compound_head(requested_page)), requested_page->flags);
}
unset_migratetype_isolate(requested_page);
if (locked_page) {
/*
* The page is now rightfully ours!
*/
locked_page_count_after = page_count(locked_page);
printk(KERN_DEBUG "Buddy: Requested pfn %lx, allocated pfn %lx with pagecount %i (was:%i)\n", page_to_pfn(requested_page), page_to_pfn(locked_page), locked_page_count_after, locked_page_count_before);
*actual_source = SOURCE_FREE_BUDDY_PAGE;
ret = CLAIMED_SUCCESSFULLY;
}
}
return ret;
}
/*
* Mark a page as having seen activity.
*
* inactive,unreferenced -> inactive,referenced
* inactive,referenced -> active,unreferenced
* active,unreferenced -> active,referenced
*
* When a newly allocated page is not yet visible, so safe for non-atomic ops,
* __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
*/
void mark_page_accessed(struct page *page)
{
page = compound_head(page);
if (!PageActive(page) && !PageUnevictable(page) &&
PageReferenced(page)) {
/*
* If the page is on the LRU, queue it for activation via
* activate_page_pvecs. Otherwise, assume the page is on a
* pagevec, mark it active and it'll be moved to the active
* LRU on the next drain.
*/
if (PageLRU(page))
activate_page(page);
else
__lru_cache_activate_page(page);
ClearPageReferenced(page);
if (page_is_file_cache(page))
workingset_activation(page);
} else if (!PageReferenced(page)) {
SetPageReferenced(page);
}
if (page_is_idle(page))
clear_page_idle(page);
}
/*
* This function is exported but must not be called by anything other
* than get_page(). It implements the slow path of get_page().
*/
bool __get_page_tail(struct page *page)
{
/*
* This takes care of get_page() if run on a tail page
* returned by one of the get_user_pages/follow_page variants.
* get_user_pages/follow_page itself doesn't need the compound
* lock because it runs __get_page_tail_foll() under the
* proper PT lock that already serializes against
* split_huge_page().
*/
unsigned long flags;
bool got;
struct page *page_head = compound_head(page);
/* Ref to put_compound_page() comment. */
if (!__compound_tail_refcounted(page_head)) {
smp_rmb();
if (likely(PageTail(page))) {
/*
* This is a hugetlbfs page or a slab
* page. __split_huge_page_refcount
* cannot race here.
*/
VM_BUG_ON_PAGE(!PageHead(page_head), page_head);
__get_page_tail_foll(page, true);
return true;
} else {
/*
* __split_huge_page_refcount run
* before us, "page" was a THP
* tail. The split page_head has been
* freed and reallocated as slab or
* hugetlbfs page of smaller order
* (only possible if reallocated as
* slab on x86).
*/
return false;
}
}
got = false;
if (likely(page != page_head && get_page_unless_zero(page_head))) {
/*
* page_head wasn't a dangling pointer but it
* may not be a head page anymore by the time
* we obtain the lock. That is ok as long as it
* can't be freed from under us.
*/
flags = compound_lock_irqsave(page_head);
/* here __split_huge_page_refcount won't run anymore */
if (likely(PageTail(page))) {
__get_page_tail_foll(page, false);
got = true;
}
compound_unlock_irqrestore(page_head, flags);
if (unlikely(!got))
put_page(page_head);
}
return got;
}
/*
* This function is exported but must not be called by anything other
* than get_page(). It implements the slow path of get_page().
*/
bool __get_page_tail(struct page *page)
{
/*
* This takes care of get_page() if run on a tail page
* returned by one of the get_user_pages/follow_page variants.
* get_user_pages/follow_page itself doesn't need the compound
* lock because it runs __get_page_tail_foll() under the
* proper PT lock that already serializes against
* split_huge_page().
*/
bool got = false;
struct page *page_head;
/*
* If this is a hugetlbfs page it cannot be split under us. Simply
* increment refcount for the head page.
*/
if (PageHuge(page)) {
page_head = compound_head(page);
atomic_inc(&page_head->_count);
got = true;
} else {
unsigned long flags;
page_head = compound_trans_head(page);
if (likely(page != page_head &&
get_page_unless_zero(page_head))) {
/* Ref to put_compound_page() comment. */
if (PageSlab(page_head)) {
if (likely(PageTail(page))) {
__get_page_tail_foll(page, false);
return true;
} else {
put_page(page_head);
return false;
}
}
/*
* page_head wasn't a dangling pointer but it
* may not be a head page anymore by the time
* we obtain the lock. That is ok as long as it
* can't be freed from under us.
*/
flags = compound_lock_irqsave(page_head);
/* here __split_huge_page_refcount won't run anymore */
if (likely(PageTail(page))) {
__get_page_tail_foll(page, false);
got = true;
}
compound_unlock_irqrestore(page_head, flags);
if (unlikely(!got))
put_page(page_head);
}
}
return got;
}
void activate_page(struct page *page)
{
struct zone *zone = page_zone(page);
page = compound_head(page);
spin_lock_irq(zone_lru_lock(zone));
__activate_page(page, mem_cgroup_page_lruvec(page, zone->zone_pgdat), NULL);
spin_unlock_irq(zone_lru_lock(zone));
}
static void put_compound_page(struct page *page)
{
page = compound_head(page);
if (put_page_testzero(page)) {
compound_page_dtor *dtor;
dtor = get_compound_page_dtor(page);
(*dtor)(page);
}
}
void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
u64 bound)
{
int idx;
u64 addr;
struct ib_device *dev = umem->context->device;
virt = max_t(u64, virt, ib_umem_start(umem));
bound = min_t(u64, bound, ib_umem_end(umem));
/* Note that during the run of this function, the
* notifiers_count of the MR is > 0, preventing any racing
* faults from completion. We might be racing with other
* invalidations, so we must make sure we free each page only
* once. */
for (addr = virt; addr < bound; addr += PAGE_SIZE) {
idx = (addr - ib_umem_start(umem)) / PAGE_SIZE;
mutex_lock(&umem->odp_data->umem_mutex);
if (umem->odp_data->page_list[idx]) {
struct page *page = umem->odp_data->page_list[idx];
#ifdef CONFIG_COMPAT_USE_COMPOUND_TRANS_HEAD
struct page *head_page = compound_trans_head(page);
#else
struct page *head_page = compound_head(page);
#endif
dma_addr_t dma_addr = umem->odp_data->dma_list[idx] &
ODP_DMA_ADDR_MASK;
WARN_ON(!dma_addr);
ib_dma_unmap_page(dev, dma_addr, PAGE_SIZE,
DMA_BIDIRECTIONAL);
if (umem->odp_data->dma_list[idx] &
ODP_WRITE_ALLOWED_BIT)
/*
* set_page_dirty prefers being called with
* the page lock. However, MMU notifiers are
* called sometimes with and sometimes without
* the lock. We rely on the umem_mutex instead
* to prevent other mmu notifiers from
* continuing and allowing the page mapping to
* be removed.
*/
set_page_dirty(head_page);
/* on demand pinning support */
if (!umem->context->invalidate_range)
put_page(page);
umem->odp_data->page_list[idx] = NULL;
umem->odp_data->dma_list[idx] = 0;
atomic_inc(&dev->odp_statistics.num_invalidation_pages);
}
mutex_unlock(&umem->odp_data->umem_mutex);
}
}
void activate_page(struct page *page)
{
page = compound_head(page);
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, __activate_page, NULL);
put_cpu_var(activate_page_pvecs);
}
}
static int hwpoison_inject(void *data, u64 val)
{
unsigned long pfn = val;
struct page *p;
struct page *hpage;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!pfn_valid(pfn))
return -ENXIO;
p = pfn_to_page(pfn);
hpage = compound_head(p);
/*
* This implies unable to support free buddy pages.
*/
if (!get_page_unless_zero(hpage))
return 0;
if (!hwpoison_filter_enable)
goto inject;
if (!PageLRU(p) && !PageHuge(p))
shake_page(p, 0);
/*
* This implies unable to support non-LRU pages.
*/
if (!PageLRU(p) && !PageHuge(p))
return 0;
/*
* do a racy check with elevated page count, to make sure PG_hwpoison
* will only be set for the targeted owner (or on a free page).
* We temporarily take page lock for try_get_mem_cgroup_from_page().
* memory_failure() will redo the check reliably inside page lock.
*/
lock_page(hpage);
err = hwpoison_filter(hpage);
unlock_page(hpage);
if (err)
return 0;
inject:
printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn);
return memory_failure(pfn, 18, MF_COUNT_INCREASED);
}
struct page *alloc_migrate_target(struct page *page, unsigned long nid,
int **resultp)
{
/*
* hugeTLB: allocate a destination page from a nearest neighbor node,
* accordance with memory policy of the user process if possible. For
* now as a simple work-around, we use the next node for destination.
* Normal page: use prefer mempolicy for destination if called by
* hotplug, use default mempolicy for destination if called by cma.
*/
if (PageHuge(page))
return alloc_huge_page_node(page_hstate(compound_head(page)),
next_node_in(page_to_nid(page),
node_online_map));
else
return alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0);
}
/*
* The performance critical leaf functions are made noinline otherwise gcc
* inlines everything into a single function which results in too much
* register pressure.
*/
static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long mask, result;
pte_t *ptep;
if (tlb_type == hypervisor) {
result = _PAGE_PRESENT_4V|_PAGE_P_4V;
if (write)
result |= _PAGE_WRITE_4V;
} else {
result = _PAGE_PRESENT_4U|_PAGE_P_4U;
if (write)
result |= _PAGE_WRITE_4U;
}
mask = result | _PAGE_SPECIAL;
ptep = pte_offset_kernel(&pmd, addr);
do {
struct page *page, *head;
pte_t pte = *ptep;
if ((pte_val(pte) & mask) != result)
return 0;
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
/* The hugepage case is simplified on sparc64 because
* we encode the sub-page pfn offsets into the
* hugepage PTEs. We could optimize this in the future
* use page_cache_add_speculative() for the hugepage case.
*/
page = pte_page(pte);
head = compound_head(page);
if (!page_cache_get_speculative(head))
return 0;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
put_page(head);
return 0;
}
pages[*nr] = page;
(*nr)++;
} while (ptep++, addr += PAGE_SIZE, addr != end);
return 1;
}
/**
* Try to claim a "free" page that is neither in the buddy system nor somewhere else
*
* This is currently disabled because it is virtually impossible to detect, if a page
* is free in the described way.
*
* To quote from memory-failure.c
*
* * We need/can do nothing about count=0 pages.
* 1) it's a free page, and therefore in safe hand:
* prep_new_page() will be the gate keeper.
* 2) it's part of a non-compound high order page.
* Implies some kernel user: cannot stop them from
* R/W the page; let's pray that the page has been
* used and will be freed some time later.
* In fact it's dangerous to directly bump up page count from 0,
* that may make page_freeze_refs()/page_unfreeze_refs() mismatch.
*
*/
inline int try_claim_free_page(struct page* requested_page, unsigned int allowed_sources, struct page** allocated_page, unsigned long* actual_source) {
int ret = CLAIMED_TRY_NEXT;
int enabled = 0;
if ( enabled && (allowed_sources & SOURCE_FREE_PAGE)) {
struct page* compound_head_page;
compound_head_page = compound_head(requested_page);
/*
* This is a heuristic: Normally all pages should be 'somewhere', so this is very likely to be 'false' for all pages
*
* Additionally this test is propably not correct anyway.
* */
if (compound_head_page == requested_page
&& !free_pages_check__just_test(requested_page) == 0
&& requested_page->lru.next == NULL && requested_page->lru.prev == NULL) {
int locked_page_count_before, locked_page_count_after;
locked_page_count_before = page_count(requested_page);
get_page(requested_page);
if (requested_page){
/*
* The page is now rightfully ours!
*/
locked_page_count_after = page_count(requested_page);
printk(KERN_DEBUG "Requested pfn %lx with pagecount %i (was:%i)\n", page_to_pfn(requested_page), locked_page_count_after, locked_page_count_before);
*actual_source = SOURCE_FREE_PAGE;
ret = CLAIMED_SUCCESSFULLY;
}else{
/**
* We could not lock the page
*/
printk(KERN_DEBUG "Requested pfn %lx but could not get it though it was _count == 0.)\n", page_to_pfn(requested_page));
}
}
}
return ret;
}
static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long mask, result;
pte_t *ptep;
if (tlb_type == hypervisor) {
result = _PAGE_PRESENT_4V|_PAGE_P_4V;
if (write)
result |= _PAGE_WRITE_4V;
} else {
result = _PAGE_PRESENT_4U|_PAGE_P_4U;
if (write)
result |= _PAGE_WRITE_4U;
}
mask = result | _PAGE_SPECIAL;
ptep = pte_offset_kernel(&pmd, addr);
do {
struct page *page, *head;
pte_t pte = *ptep;
if ((pte_val(pte) & mask) != result)
return 0;
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
head = compound_head(page);
if (!page_cache_get_speculative(head))
return 0;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
put_page(head);
return 0;
}
if (head != page)
get_huge_page_tail(page);
pages[*nr] = page;
(*nr)++;
} while (ptep++, addr += PAGE_SIZE, addr != end);
return 1;
}
static void put_compound_page(struct page *page)
{
struct page *page_head;
/*
* We see the PageCompound set and PageTail not set, so @page maybe:
* 1. hugetlbfs head page, or
* 2. THP head page.
*/
if (likely(!PageTail(page))) {
if (put_page_testzero(page)) {
/*
* By the time all refcounts have been released
* split_huge_page cannot run anymore from under us.
*/
if (PageHead(page))
__put_compound_page(page);
else
__put_single_page(page);
}
return;
}
/*
* We see the PageCompound set and PageTail set, so @page maybe:
* 1. a tail hugetlbfs page, or
* 2. a tail THP page, or
* 3. a split THP page.
*
* Case 3 is possible, as we may race with
* __split_huge_page_refcount tearing down a THP page.
*/
page_head = compound_head(page);
if (!__compound_tail_refcounted(page_head))
put_unrefcounted_compound_page(page_head, page);
else
put_refcounted_compound_page(page_head, page);
}
static int ept_set_epte(struct vmx_vcpu *vcpu, int make_write,
unsigned long gpa, unsigned long hva)
{
int ret;
epte_t *epte, flags;
struct page *page;
unsigned huge_shift;
int level;
ret = get_user_pages_fast(hva, 1, make_write, &page);
if (ret != 1) {
ret = ept_set_pfnmap_epte(vcpu, make_write, gpa, hva);
if (ret)
printk(KERN_ERR "ept: failed to get user page %lx\n", hva);
return ret;
}
spin_lock(&vcpu->ept_lock);
huge_shift = compound_order(compound_head(page)) + PAGE_SHIFT;
level = 0;
if (huge_shift == 30)
level = 2;
else if (huge_shift == 21)
level = 1;
ret = ept_lookup_gpa(vcpu, (void *) gpa,
level, 1, &epte);
if (ret) {
spin_unlock(&vcpu->ept_lock);
put_page(page);
printk(KERN_ERR "ept: failed to lookup EPT entry\n");
return ret;
}
if (epte_present(*epte)) {
if (!epte_big(*epte) && level == 2)
ept_clear_l2_epte(epte);
else if (!epte_big(*epte) && level == 1)
ept_clear_l1_epte(epte);
else
ept_clear_epte(epte);
}
flags = __EPTE_READ | __EPTE_EXEC |
__EPTE_TYPE(EPTE_TYPE_WB) | __EPTE_IPAT;
if (make_write)
flags |= __EPTE_WRITE;
if (vcpu->ept_ad_enabled) {
/* premark A/D to avoid extra memory references */
flags |= __EPTE_A;
if (make_write)
flags |= __EPTE_D;
}
if (level) {
struct page *tmp = page;
page = compound_head(page);
get_page(page);
put_page(tmp);
flags |= __EPTE_SZ;
}
*epte = epte_addr(page_to_phys(page)) | flags;
spin_unlock(&vcpu->ept_lock);
return 0;
}
/**
* 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);
}
static __always_inline
void put_refcounted_compound_page(struct page *page_head, struct page *page)
{
if (likely(page != page_head && get_page_unless_zero(page_head))) {
unsigned long flags;
/*
* @page_head wasn't a dangling pointer but it may not
* be a head page anymore by the time we obtain the
* lock. That is ok as long as it can't be freed from
* under us.
*/
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
/*
* The @page_head may have been freed
* and reallocated as a compound page
* of smaller order and then freed
* again. All we know is that it
* cannot have become: a THP page, a
* compound page of higher order, a
* tail page. That is because we
* still hold the refcount of the
* split THP tail and page_head was
* the THP head before the split.
*/
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
return;
}
VM_BUG_ON_PAGE(page_head != compound_head(page), page);
/*
* We can release the refcount taken by
* get_page_unless_zero() now that
* __split_huge_page_refcount() is blocked on the
* compound_lock.
*/
if (put_page_testzero(page_head))
VM_BUG_ON_PAGE(1, page_head);
/* __split_huge_page_refcount will wait now */
VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page);
atomic_dec(&page->_mapcount);
VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head);
VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
} else {
/* @page_head is a dangling pointer */
VM_BUG_ON_PAGE(PageTail(page), page);
goto out_put_single;
}
}
static void put_compound_page(struct page *page)
{
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
struct page *page_head = compound_head(page);
if (likely(page != page_head &&
get_page_unless_zero(page_head))) {
unsigned long flags;
/*
* THP can not break up slab pages so avoid taking
* compound_lock(). Slab performs non-atomic bit ops
* on page->flags for better performance. In particular
* slab_unlock() in slub used to be a hot path. It is
* still hot on arches that do not support
* this_cpu_cmpxchg_double().
*/
if (PageSlab(page_head) || PageHeadHuge(page_head)) {
if (likely(PageTail(page))) {
/*
* __split_huge_page_refcount
* cannot race here.
*/
VM_BUG_ON(!PageHead(page_head));
atomic_dec(&page->_mapcount);
if (put_page_testzero(page_head))
VM_BUG_ON(1);
if (put_page_testzero(page_head))
__put_compound_page(page_head);
return;
} else
/*
* __split_huge_page_refcount
* run before us, "page" was a
* THP tail. The split
* page_head has been freed
* and reallocated as slab or
* hugetlbfs page of smaller
* order (only possible if
* reallocated as slab on
* x86).
*/
goto skip_lock;
}
/*
* page_head wasn't a dangling pointer but it
* may not be a head page anymore by the time
* we obtain the lock. That is ok as long as it
* can't be freed from under us.
*/
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
skip_lock:
if (put_page_testzero(page_head)) {
/*
* The head page may have been
* freed and reallocated as a
* compound page of smaller
* order and then freed again.
* All we know is that it
* cannot have become: a THP
* page, a compound page of
* higher order, a tail page.
* That is because we still
* hold the refcount of the
* split THP tail and
* page_head was the THP head
* before the split.
*/
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
return;
}
VM_BUG_ON(page_head != page->first_page);
/*
* We can release the refcount taken by
* get_page_unless_zero() now that
* __split_huge_page_refcount() is blocked on
* the compound_lock.
*/
if (put_page_testzero(page_head))
VM_BUG_ON(1);
/* __split_huge_page_refcount will wait now */
VM_BUG_ON(page_mapcount(page) <= 0);
atomic_dec(&page->_mapcount);
VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
VM_BUG_ON(atomic_read(&page->_count) != 0);
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
} else {
/* page_head is a dangling pointer */
VM_BUG_ON(PageTail(page));
goto out_put_single;
}
} else if (put_page_testzero(page)) {
if (PageHead(page))
__put_compound_page(page);
else
__put_single_page(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;
};
static void put_compound_page(struct page *page)
{
struct page *page_head;
if (likely(!PageTail(page))) {
if (put_page_testzero(page)) {
/*
* By the time all refcounts have been released
* split_huge_page cannot run anymore from under us.
*/
if (PageHead(page))
__put_compound_page(page);
else
__put_single_page(page);
}
return;
}
/* __split_huge_page_refcount can run under us */
page_head = compound_head(page);
/*
* THP can not break up slab pages so avoid taking
* compound_lock() and skip the tail page refcounting (in
* _mapcount) too. Slab performs non-atomic bit ops on
* page->flags for better performance. In particular
* slab_unlock() in slub used to be a hot path. It is still
* hot on arches that do not support
* this_cpu_cmpxchg_double().
*
* If "page" is part of a slab or hugetlbfs page it cannot be
* splitted and the head page cannot change from under us. And
* if "page" is part of a THP page under splitting, if the
* head page pointed by the THP tail isn't a THP head anymore,
* we'll find PageTail clear after smp_rmb() and we'll treat
* it as a single page.
*/
if (!__compound_tail_refcounted(page_head)) {
/*
* If "page" is a THP tail, we must read the tail page
* flags after the head page flags. The
* split_huge_page side enforces write memory barriers
* between clearing PageTail and before the head page
* can be freed and reallocated.
*/
smp_rmb();
if (likely(PageTail(page))) {
/*
* __split_huge_page_refcount cannot race
* here.
*/
VM_BUG_ON_PAGE(!PageHead(page_head), page_head);
VM_BUG_ON_PAGE(page_mapcount(page) != 0, page);
if (put_page_testzero(page_head)) {
/*
* If this is the tail of a slab
* compound page, the tail pin must
* not be the last reference held on
* the page, because the PG_slab
* cannot be cleared before all tail
* pins (which skips the _mapcount
* tail refcounting) have been
* released. For hugetlbfs the tail
* pin may be the last reference on
* the page instead, because
* PageHeadHuge will not go away until
* the compound page enters the buddy
* allocator.
*/
VM_BUG_ON_PAGE(PageSlab(page_head), page_head);
__put_compound_page(page_head);
}
return;
} else
/*
* __split_huge_page_refcount run before us,
* "page" was a THP tail. The split page_head
* has been freed and reallocated as slab or
* hugetlbfs page of smaller order (only
* possible if reallocated as slab on x86).
*/
goto out_put_single;
}
if (likely(page != page_head && get_page_unless_zero(page_head))) {
unsigned long flags;
/*
* page_head wasn't a dangling pointer but it may not
* be a head page anymore by the time we obtain the
* lock. That is ok as long as it can't be freed from
* under us.
*/
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
/*
* The head page may have been freed
* and reallocated as a compound page
* of smaller order and then freed
* again. All we know is that it
* cannot have become: a THP page, a
* compound page of higher order, a
* tail page. That is because we
* still hold the refcount of the
* split THP tail and page_head was
* the THP head before the split.
*/
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
return;
}
VM_BUG_ON_PAGE(page_head != page->first_page, page);
/*
* We can release the refcount taken by
* get_page_unless_zero() now that
* __split_huge_page_refcount() is blocked on the
* compound_lock.
*/
if (put_page_testzero(page_head))
VM_BUG_ON_PAGE(1, page_head);
/* __split_huge_page_refcount will wait now */
VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page);
atomic_dec(&page->_mapcount);
VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head);
VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
compound_unlock_irqrestore(page_head, flags);
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
} else {
/* page_head is a dangling pointer */
VM_BUG_ON_PAGE(PageTail(page), page);
goto out_put_single;
}
}
static void put_compound_page(struct page *page)
{
/*
* hugetlbfs pages cannot be split from under us. If this is a
* hugetlbfs page, check refcount on head page and release the page if
* the refcount becomes zero.
*/
if (PageHuge(page)) {
page = compound_head(page);
if (put_page_testzero(page))
__put_compound_page(page);
return;
}
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
struct page *page_head = compound_trans_head(page);
if (likely(page != page_head &&
get_page_unless_zero(page_head))) {
unsigned long flags;
/*
* THP can not break up slab pages so avoid taking
* compound_lock(). Slab performs non-atomic bit ops
* on page->flags for better performance. In particular
* slab_unlock() in slub used to be a hot path. It is
* still hot on arches that do not support
* this_cpu_cmpxchg_double().
*/
if (PageSlab(page_head)) {
if (PageTail(page)) {
if (put_page_testzero(page_head))
VM_BUG_ON(1);
atomic_dec(&page->_mapcount);
goto skip_lock_tail;
} else
goto skip_lock;
}
/*
* page_head wasn't a dangling pointer but it
* may not be a head page anymore by the time
* we obtain the lock. That is ok as long as it
* can't be freed from under us.
*/
flags = compound_lock_irqsave(page_head);
if (unlikely(!PageTail(page))) {
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
skip_lock:
if (put_page_testzero(page_head))
__put_single_page(page_head);
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
return;
}
VM_BUG_ON(page_head != page->first_page);
/*
* We can release the refcount taken by
* get_page_unless_zero() now that
* __split_huge_page_refcount() is blocked on
* the compound_lock.
*/
if (put_page_testzero(page_head))
VM_BUG_ON(1);
/* __split_huge_page_refcount will wait now */
VM_BUG_ON(page_mapcount(page) <= 0);
atomic_dec(&page->_mapcount);
VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
VM_BUG_ON(atomic_read(&page->_count) != 0);
compound_unlock_irqrestore(page_head, flags);
skip_lock_tail:
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
else
__put_single_page(page_head);
}
} else {
/* page_head is a dangling pointer */
VM_BUG_ON(PageTail(page));
goto out_put_single;
}
} else if (put_page_testzero(page)) {
if (PageHead(page))
__put_compound_page(page);
else
__put_single_page(page);
}
}
