void put_page(struct page *page)
{
if (unlikely(PageCompound(page)))
put_compound_page(page);
else if (put_page_testzero(page))
__put_single_page(page);
}
/* used by __split_huge_page_refcount() */
void lru_add_page_tail(struct zone* zone,
struct page *page, struct page *page_tail)
{
int active;
enum lru_list lru;
const int file = 0;
struct list_head *head;
VM_BUG_ON(!PageHead(page));
VM_BUG_ON(PageCompound(page_tail));
VM_BUG_ON(PageLRU(page_tail));
VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&zone->lru_lock));
SetPageLRU(page_tail);
if (page_evictable(page_tail, NULL)) {
if (PageActive(page)) {
SetPageActive(page_tail);
active = 1;
lru = LRU_ACTIVE_ANON;
} else {
active = 0;
lru = LRU_INACTIVE_ANON;
}
update_page_reclaim_stat(zone, page_tail, file, active);
if (likely(PageLRU(page)))
head = page->lru.prev;
else
head = &zone->lru[lru].list;
__add_page_to_lru_list(zone, page_tail, lru, head);
} else {
SetPageUnevictable(page_tail);
add_page_to_lru_list(zone, page_tail, LRU_UNEVICTABLE);
}
}
void put_page(struct page *page)
{
if (unlikely(PageCompound(page)))
put_compound_page(page);
else if (put_page_testzero(page))
__page_cache_release(page);
}
void __put_page(struct page *page)
{
if (unlikely(PageCompound(page)))
__put_compound_page(page);
else
__put_single_page(page);
}
void __dump_page(struct page *page, const char *reason)
{
struct address_space *mapping = page_mapping(page);
bool page_poisoned = PagePoisoned(page);
int mapcount;
/*
* If struct page is poisoned don't access Page*() functions as that
* leads to recursive loop. Page*() check for poisoned pages, and calls
* dump_page() when detected.
*/
if (page_poisoned) {
pr_warn("page:%px is uninitialized and poisoned", page);
goto hex_only;
}
/*
* Avoid VM_BUG_ON() in page_mapcount().
* page->_mapcount space in struct page is used by sl[aou]b pages to
* encode own info.
*/
mapcount = PageSlab(page) ? 0 : page_mapcount(page);
pr_warn("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
page, page_ref_count(page), mapcount,
page->mapping, page_to_pgoff(page));
if (PageCompound(page))
pr_cont(" compound_mapcount: %d", compound_mapcount(page));
pr_cont("\n");
if (PageAnon(page))
pr_warn("anon ");
else if (PageKsm(page))
pr_warn("ksm ");
else if (mapping) {
pr_warn("%ps ", mapping->a_ops);
if (mapping->host->i_dentry.first) {
struct dentry *dentry;
dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias);
pr_warn("name:\"%pd\" ", dentry);
}
}
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags);
hex_only:
print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
sizeof(unsigned long), page,
sizeof(struct page), false);
if (reason)
pr_warn("page dumped because: %s\n", reason);
#ifdef CONFIG_MEMCG
if (!page_poisoned && page->mem_cgroup)
pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup);
#endif
}
static void __lru_cache_add(struct page *page)
{
struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
__pagevec_lru_add(pvec);
put_cpu_var(lru_add_pvec);
}
/**
* release_pages:释放pages页框数组(只有count = 0时,才正真的被回收)
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
unsigned long uninitialized_var(flags);
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
/*减少page的引用次数*/
if (!put_page_testzero(page))
continue;
/*page的引用次数为0,则page从zone LRU链表中删除*/
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
VM_BUG_ON(!PageLRU(page));
/*清空页的LRU属性*/
__ClearPageLRU(page);
del_page_from_lru(zone, page);
}
/*page加入到pages_to_free页缓存中*/
if (!pagevec_add(&pages_to_free, page)) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
__pagevec_free(&pages_to_free);
pagevec_reinit(&pages_to_free);
}
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
pagevec_free(&pages_to_free);
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_inactive_list(): we recheck
* the page count inside the lock to see whether shrink_inactive_list()
* grabbed the page via the LRU. If it did, give up: shrink_inactive_list()
* will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
unsigned long uninitialized_var(flags);
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
if (!put_page_testzero(page))
continue;
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
VM_BUG_ON(!PageLRU(page));
__ClearPageLRU(page);
del_page_from_lru(zone, page);
} else if (PageIONBacked(page)) {
ClearPageActive(page);
ClearPageUnevictable(page);
}
if (!pagevec_add(&pages_to_free, page)) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
__pagevec_free(&pages_to_free);
pagevec_reinit(&pages_to_free);
}
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
pagevec_free(&pages_to_free);
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_inactive_list(): we recheck
* the page count inside the lock to see whether shrink_inactive_list()
* grabbed the page via the LRU. If it did, give up: shrink_inactive_list()
* will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
unsigned long uninitialized_var(flags);
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
#ifdef CONFIG_OXNAS_FAST_READS_AND_WRITES
WARN_ON(PageIncoherentSendfile(page));
#endif // CONFIG_OXNAS_FAST_READS_AND_WRITES
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
if (!put_page_testzero(page))
continue;
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
VM_BUG_ON(!PageLRU(page));
__ClearPageLRU(page);
del_page_from_lru(zone, page);
}
if (!pagevec_add(&pages_to_free, page)) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
__pagevec_free(&pages_to_free);
pagevec_reinit(&pages_to_free);
}
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
pagevec_free(&pages_to_free);
}
/**
* deactivate_page - deactivate a page
* @page: page to deactivate
*
* deactivate_page() moves @page to the inactive list if @page was on the active
* list and was not an unevictable page. This is done to accelerate the reclaim
* of @page.
*/
void deactivate_page(struct page *page)
{
if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
put_cpu_var(lru_deactivate_pvecs);
}
}
/* used by __split_huge_page_refcount() */
void lru_add_page_tail(struct page *page, struct page *page_tail,
struct lruvec *lruvec, struct list_head *list)
{
int uninitialized_var(active);
enum lru_list lru;
const int file = 0;
VM_BUG_ON(!PageHead(page));
VM_BUG_ON(PageCompound(page_tail));
VM_BUG_ON(PageLRU(page_tail));
VM_BUG_ON(NR_CPUS != 1 &&
!spin_is_locked(&lruvec_zone(lruvec)->lru_lock));
if (!list)
SetPageLRU(page_tail);
if (page_evictable(page_tail)) {
if (PageActive(page)) {
SetPageActive(page_tail);
active = 1;
lru = LRU_ACTIVE_ANON;
} else {
active = 0;
lru = LRU_INACTIVE_ANON;
}
} else {
SetPageUnevictable(page_tail);
lru = LRU_UNEVICTABLE;
}
if (likely(PageLRU(page)))
list_add_tail(&page_tail->lru, &page->lru);
else if (list) {
/* page reclaim is reclaiming a huge page */
get_page(page_tail);
list_add_tail(&page_tail->lru, list);
} else {
struct list_head *list_head;
/*
* Head page has not yet been counted, as an hpage,
* so we must account for each subpage individually.
*
* Use the standard add function to put page_tail on the list,
* but then correct its position so they all end up in order.
*/
add_page_to_lru_list(page_tail, lruvec, lru);
list_head = page_tail->lru.prev;
list_move_tail(&page_tail->lru, list_head);
}
if (!PageUnevictable(page))
update_page_reclaim_stat(lruvec, file, active);
}
/**
* mark_page_lazyfree - make an anon page lazyfree
* @page: page to deactivate
*
* mark_page_lazyfree() moves @page to the inactive file list.
* This is done to accelerate the reclaim of @page.
*/
void mark_page_lazyfree(struct page *page)
{
if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
!PageSwapCache(page) && !PageUnevictable(page)) {
struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs);
get_page(page);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
put_cpu_var(lru_lazyfree_pvecs);
}
}
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);
}
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_cache(): we recheck the
* page count inside the lock to see whether shrink_cache grabbed the page
* via the LRU. If it did, give up: shrink_cache will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
unsigned long uninitialized_var(flags);
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
// dyc: if page->ref not zero, continue
if (!put_page_testzero(page))
continue;
// dyc: if in url, remove from it
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
VM_BUG_ON(!PageLRU(page));
__ClearPageLRU(page);
del_page_from_lru(zone, page);
}
// dyc: if no space available after adding
if (!pagevec_add(&pages_to_free, page)) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
// dyc: return page to buddy system
__pagevec_free(&pages_to_free);
pagevec_reinit(&pages_to_free);
}
} // for (i = 0; i < nr; i++)
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
pagevec_free(&pages_to_free);
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_inactive_list(): we recheck
* the page count inside the lock to see whether shrink_inactive_list()
* grabbed the page via the LRU. If it did, give up: shrink_inactive_list()
* will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
LIST_HEAD(pages_to_free);
struct zone *zone = NULL;
struct lruvec *lruvec;
unsigned long uninitialized_var(flags);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
if (!put_page_testzero(page))
continue;
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
VM_BUG_ON(!PageLRU(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);
list_add(&page->lru, &pages_to_free);
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
free_hot_cold_page_list(&pages_to_free, cold);
}
/*
* Writeback is about to end against a page which has been marked for immediate
* reclaim. If it still appears to be reclaimable, move it to the tail of the
* inactive list.
*/
void rotate_reclaimable_page(struct page *page)
{
if (!PageLocked(page) && !PageDirty(page) &&
!PageUnevictable(page) && PageLRU(page)) {
struct pagevec *pvec;
unsigned long flags;
get_page(page);
local_irq_save(flags);
pvec = this_cpu_ptr(&lru_rotate_pvecs);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_move_tail(pvec);
local_irq_restore(flags);
}
}
void put_page(struct page *page)
{
if (unlikely(PageCompound(page))) {
page = (struct page *)page_private(page);
if (put_page_testzero(page)) {
void (*dtor)(struct page *page);
dtor = (void (*)(struct page *))page[1].mapping;
(*dtor)(page);
}
return;
}
if (put_page_testzero(page))
__page_cache_release(page);
}
int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
{
struct mm_struct *mm;
struct vm_area_struct *vma;
struct page *page;
void *old_buf = buf;
mm = get_task_mm(tsk);
if (!mm)
return 0;
down_read(&mm->mmap_sem);
/* ignore errors, just check how much was sucessfully transfered */
while (len) {
int bytes, ret, offset;
void *maddr;
ret = get_user_pages(tsk, mm, addr, 1,
write, 1, &page, &vma);
if (ret <= 0)
break;
bytes = len;
offset = addr & (PAGE_SIZE-1);
if (bytes > PAGE_SIZE-offset)
bytes = PAGE_SIZE-offset;
maddr = kmap(page);
if (write) {
copy_to_user_page(vma, page, addr,
maddr + offset, buf, bytes);
if (!PageCompound(page))
set_page_dirty_lock(page);
} else {
copy_from_user_page(vma, page, addr,
buf, maddr + offset, bytes);
}
kunmap(page);
page_cache_release(page);
len -= bytes;
buf += bytes;
addr += bytes;
}
up_read(&mm->mmap_sem);
mmput(mm);
return buf - old_buf;
}
void put_page(struct page *page)
{
#ifdef CONFIG_OXNAS_FAST_READS_AND_WRITES
if (PageIncoherentSendfile(page)) {
fast_put(page);
} else {
#endif // CONFIG_OXNAS_FAST_READS_AND_WRITES
if (unlikely(PageCompound(page))) {
put_compound_page(page);
} else if (put_page_testzero(page)) {
__page_cache_release(page);
}
#ifdef CONFIG_OXNAS_FAST_READS_AND_WRITES
}
#endif // CONFIG_OXNAS_FAST_READS_AND_WRITES
}
/**
* deactivate_file_page - forcefully deactivate a file page
* @page: page to deactivate
*
* This function hints the VM that @page is a good reclaim candidate,
* for example if its invalidation fails due to the page being dirty
* or under writeback.
*/
void deactivate_file_page(struct page *page)
{
/*
* In a workload with many unevictable page such as mprotect,
* unevictable page deactivation for accelerating reclaim is pointless.
*/
if (PageUnevictable(page))
return;
if (likely(get_page_unless_zero(page))) {
struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
if (!pagevec_add(pvec, page) || PageCompound(page))
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
put_cpu_var(lru_deactivate_file_pvecs);
}
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_cache(): we recheck the
* page count inside the lock to see whether shrink_cache grabbed the page
* via the LRU. If it did, give up: shrink_cache will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
struct zone *pagezone;
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irq(&zone->lru_lock);
zone = NULL;
}
put_compound_page(page);
continue;
}
if (!put_page_testzero(page))
continue;
pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irq(&zone->lru_lock);
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
if (TestClearPageLRU(page))
del_page_from_lru(zone, page);
if (page_count(page) == 0) {
if (!pagevec_add(&pages_to_free, page)) {
spin_unlock_irq(&zone->lru_lock);
__pagevec_free(&pages_to_free);
pagevec_reinit(&pages_to_free);
zone = NULL; /* No lock is held */
}
}
}
if (zone)
spin_unlock_irq(&zone->lru_lock);
pagevec_free(&pages_to_free);
}
void __put_page(struct page *page)
{
if (is_zone_device_page(page)) {
put_dev_pagemap(page->pgmap);
/*
* The page belongs to the device that created pgmap. Do
* not return it to page allocator.
*/
return;
}
if (unlikely(PageCompound(page)))
__put_compound_page(page);
else
__put_single_page(page);
}
void __dump_page(struct page *page, const char *reason)
{
bool page_poisoned = PagePoisoned(page);
int mapcount;
/*
* If struct page is poisoned don't access Page*() functions as that
* leads to recursive loop. Page*() check for poisoned pages, and calls
* dump_page() when detected.
*/
if (page_poisoned) {
pr_emerg("page:%px is uninitialized and poisoned", page);
goto hex_only;
}
/*
* Avoid VM_BUG_ON() in page_mapcount().
* page->_mapcount space in struct page is used by sl[aou]b pages to
* encode own info.
*/
mapcount = PageSlab(page) ? 0 : page_mapcount(page);
pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
page, page_ref_count(page), mapcount,
page->mapping, page_to_pgoff(page));
if (PageCompound(page))
pr_cont(" compound_mapcount: %d", compound_mapcount(page));
pr_cont("\n");
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
hex_only:
print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32,
sizeof(unsigned long), page,
sizeof(struct page), false);
if (reason)
pr_alert("page dumped because: %s\n", reason);
#ifdef CONFIG_MEMCG
if (!page_poisoned && page->mem_cgroup)
pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
#endif
}
/* used by __split_huge_page_refcount() */
void lru_add_page_tail(struct zone* zone,
struct page *page, struct page *page_tail)
{
int active;
enum lru_list lru;
const int file = 0;
VM_BUG_ON(!PageHead(page));
VM_BUG_ON(PageCompound(page_tail));
VM_BUG_ON(PageLRU(page_tail));
VM_BUG_ON(!spin_is_locked(&zone->lru_lock));
SetPageLRU(page_tail);
if (page_evictable(page_tail, NULL)) {
if (PageActive(page)) {
SetPageActive(page_tail);
active = 1;
lru = LRU_ACTIVE_ANON;
} else {
active = 0;
lru = LRU_INACTIVE_ANON;
}
update_page_reclaim_stat(zone, page_tail, file, active);
} else {
SetPageUnevictable(page_tail);
lru = LRU_UNEVICTABLE;
}
if (likely(PageLRU(page)))
list_add_tail(&page_tail->lru, &page->lru);
else {
struct list_head *list_head;
/*
* Head page has not yet been counted, as an hpage,
* so we must account for each subpage individually.
*
* Use the standard add function to put page_tail on the list,
* but then correct its position so they all end up in order.
*/
add_page_to_lru_list(zone, page_tail, lru);
list_head = page_tail->lru.prev;
list_move_tail(&page_tail->lru, list_head);
}
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_inactive_list(): we recheck
* the page count inside the lock to see whether shrink_inactive_list()
* grabbed the page via the LRU. If it did, give up: shrink_inactive_list()
* will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
LIST_HEAD(pages_to_free);
struct zone *zone = NULL;
unsigned long uninitialized_var(flags);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
if (!put_page_testzero(page))
continue;
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
VM_BUG_ON(!PageLRU(page));
__ClearPageLRU(page);
del_page_from_lru_list(zone, page, page_off_lru(page));
}
list_add(&page->lru, &pages_to_free);
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
free_hot_cold_page_list(&pages_to_free, cold);
}
/*
* split_page takes a non-compound higher-order page, and splits it into
* n (1<<order) sub-pages: page[0..n]
* Each sub-page must be freed individually.
*
* Note: this is probably too low level an operation for use in drivers.
* Please consult with lkml before using this in your driver.
*/
void split_page(struct page *page, unsigned int order)
{
int i;
VM_BUG_ON(PageCompound(page));
VM_BUG_ON(!page_count(page));
#ifdef CONFIG_KMEMCHECK
/*
* Split shadow pages too, because free(page[0]) would
* otherwise free the whole shadow.
*/
if (kmemcheck_page_is_tracked(page))
split_page(virt_to_page(page[0].shadow), order);
#endif
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
}
/*
* Return the total memory allocated for this pointer, not
* just what the caller asked for.
*
* Doesn't have to be accurate, i.e. may have races.
*/
unsigned int kobjsize(const void *objp)
{
struct page *page;
/*
* If the object we have should not have ksize performed on it,
* return size of 0
*/
if (!objp || !virt_addr_valid(objp))
return 0;
page = virt_to_head_page(objp);
/*
* If the allocator sets PageSlab, we know the pointer came from
* kmalloc().
*/
if (PageSlab(page))
return ksize(objp);
/*
* If it's not a compound page, see if we have a matching VMA
* region. This test is intentionally done in reverse order,
* so if there's no VMA, we still fall through and hand back
* PAGE_SIZE for 0-order pages.
*/
if (!PageCompound(page)) {
struct vm_area_struct *vma;
vma = find_vma(current->mm, (unsigned long)objp);
if (vma)
return vma->vm_end - vma->vm_start;
}
/*
* The ksize() function is only guaranteed to work for pointers
* returned by kmalloc(). So handle arbitrary pointers here.
*/
return PAGE_SIZE << compound_order(page);
}
/* used by __split_huge_page_refcount() */
void lru_add_page_tail(struct page *page, struct page *page_tail,
struct lruvec *lruvec, struct list_head *list)
{
const int file = 0;
VM_BUG_ON_PAGE(!PageHead(page), page);
VM_BUG_ON_PAGE(PageCompound(page_tail), page);
VM_BUG_ON_PAGE(PageLRU(page_tail), page);
VM_BUG_ON(NR_CPUS != 1 &&
!spin_is_locked(&lruvec_pgdat(lruvec)->lru_lock));
if (!list)
SetPageLRU(page_tail);
if (likely(PageLRU(page)))
list_add_tail(&page_tail->lru, &page->lru);
else if (list) {
/* page reclaim is reclaiming a huge page */
get_page(page_tail);
list_add_tail(&page_tail->lru, list);
} else {
struct list_head *list_head;
/*
* Head page has not yet been counted, as an hpage,
* so we must account for each subpage individually.
*
* Use the standard add function to put page_tail on the list,
* but then correct its position so they all end up in order.
*/
add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail));
list_head = page_tail->lru.prev;
list_move_tail(&page_tail->lru, list_head);
}
if (!PageUnevictable(page))
update_page_reclaim_stat(lruvec, file, PageActive(page_tail));
}
/*
* This function checks for proper alignment of input addr and len parameters.
*/
int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
{
if (len & ~HPAGE_MASK)
return -EINVAL;
if (addr & ~HPAGE_MASK)
return -EINVAL;
return 0;
}
#if 0 /* This is just for testing */
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
unsigned long start = address;
int length = 1;
int nr;
struct page *page;
struct vm_area_struct *vma;
vma = find_vma(mm, addr);
if (!vma || !is_vm_hugetlb_page(vma))
return ERR_PTR(-EINVAL);
pte = huge_pte_offset(mm, address);
/* hugetlb should be locked, and hence, prefaulted */
WARN_ON(!pte || pte_none(*pte));
page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
WARN_ON(!PageCompound(page));
return page;
}
static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
struct xen_netif_tx_request *tx)
{
struct netfront_info *np = netdev_priv(dev);
char *data = skb->data;
unsigned long mfn;
RING_IDX prod = np->tx.req_prod_pvt;
int frags = skb_shinfo(skb)->nr_frags;
unsigned int offset = offset_in_page(data);
unsigned int len = skb_headlen(skb);
unsigned int id;
grant_ref_t ref;
int i;
/* While the header overlaps a page boundary (including being
larger than a page), split it it into page-sized chunks. */
while (len > PAGE_SIZE - offset) {
tx->size = PAGE_SIZE - offset;
tx->flags |= XEN_NETTXF_more_data;
len -= tx->size;
data += tx->size;
offset = 0;
id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
np->tx_skbs[id].skb = skb_get(skb);
tx = RING_GET_REQUEST(&np->tx, prod++);
tx->id = id;
ref = gnttab_claim_grant_reference(&np->gref_tx_head);
BUG_ON((signed short)ref < 0);
mfn = virt_to_mfn(data);
gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id,
mfn, GNTMAP_readonly);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = len;
tx->flags = 0;
}
/* Grant backend access to each skb fragment page. */
for (i = 0; i < frags; i++) {
skb_frag_t *frag = skb_shinfo(skb)->frags + i;
struct page *page = skb_frag_page(frag);
len = skb_frag_size(frag);
offset = frag->page_offset;
/* Data must not cross a page boundary. */
BUG_ON(len + offset > PAGE_SIZE<<compound_order(page));
/* Skip unused frames from start of page */
page += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;
while (len > 0) {
unsigned long bytes;
BUG_ON(offset >= PAGE_SIZE);
bytes = PAGE_SIZE - offset;
if (bytes > len)
bytes = len;
tx->flags |= XEN_NETTXF_more_data;
id = get_id_from_freelist(&np->tx_skb_freelist,
np->tx_skbs);
np->tx_skbs[id].skb = skb_get(skb);
tx = RING_GET_REQUEST(&np->tx, prod++);
tx->id = id;
ref = gnttab_claim_grant_reference(&np->gref_tx_head);
BUG_ON((signed short)ref < 0);
mfn = pfn_to_mfn(page_to_pfn(page));
gnttab_grant_foreign_access_ref(ref,
np->xbdev->otherend_id,
mfn, GNTMAP_readonly);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = bytes;
tx->flags = 0;
offset += bytes;
len -= bytes;
/* Next frame */
if (offset == PAGE_SIZE && len) {
BUG_ON(!PageCompound(page));
page++;
offset = 0;
}
}
}
np->tx.req_prod_pvt = prod;
}
