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_trans_head(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);
VM_BUG_ON(PageHead(page_head));
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);
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);
}
}
/*
* 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_trans_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(!PageHead(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().
*/
unsigned long flags;
bool got = false;
struct page *page_head = compound_trans_head(page);
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 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);
}
}
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_trans_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(!PageHead(page_head));
VM_BUG_ON(page_mapcount(page) != 0);
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(PageSlab(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_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;
}
}
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_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);
}
}
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_trans_head(page);
if (likely(page != page_head &&
get_page_unless_zero(page_head))) {
unsigned long flags;
if (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);
VM_BUG_ON(PageHead(page_head));
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);
}
}
struct page *testfn(struct page *page)
{
return compound_trans_head(page);
}
