/*
* Clean and dirty swap cache.
*
* Dirty swap cache page is tricky to handle. The page could live both in page
* cache and swap cache(ie. page is freshly swapped in). So it could be
* referenced concurrently by 2 types of PTEs:
* normal PTEs and swap PTEs. We try to handle them consistently by calling
* try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs,
* and then
* - clear dirty bit to prevent IO
* - remove from LRU
* - but keep in the swap cache, so that when we return to it on
* a later page fault, we know the application is accessing
* corrupted data and shall be killed (we installed simple
* interception code in do_swap_page to catch it).
*
* Clean swap cache pages can be directly isolated. A later page fault will
* bring in the known good data from disk.
*/
static int me_swapcache_dirty(struct page *p, unsigned long pfn)
{
ClearPageDirty(p);
/* Trigger EIO in shmem: */
ClearPageUptodate(p);
if (!delete_from_lru_cache(p))
return MF_DELAYED;
else
return MF_FAILED;
}
static int me_swapcache_clean(struct page *p, unsigned long pfn)
{
delete_from_swap_cache(p);
if (!delete_from_lru_cache(p))
return MF_RECOVERED;
else
return MF_FAILED;
}
/*
* Huge pages. Needs work.
* Issues:
* - Error on hugepage is contained in hugepage unit (not in raw page unit.)
* To narrow down kill region to one page, we need to break up pmd.
*/
static int me_huge_page(struct page *p, unsigned long pfn)
{
int res = 0;
struct page *hpage = compound_head(p);
if (!PageHuge(hpage))
return MF_DELAYED;
/*
* We can safely recover from error on free or reserved (i.e.
* not in-use) hugepage by dequeuing it from freelist.
* To check whether a hugepage is in-use or not, we can't use
* page->lru because it can be used in other hugepage operations,
* such as __unmap_hugepage_range() and gather_surplus_pages().
* So instead we use page_mapping() and PageAnon().
* We assume that this function is called with page lock held,
* so there is no race between isolation and mapping/unmapping.
*/
if (!(page_mapping(hpage) || PageAnon(hpage))) {
res = dequeue_hwpoisoned_huge_page(hpage);
if (!res)
return MF_RECOVERED;
}
return MF_DELAYED;
}
/*
* Various page states we can handle.
*
* A page state is defined by its current page->flags bits.
* The table matches them in order and calls the right handler.
*
* This is quite tricky because we can access page at any time
* in its live cycle, so all accesses have to be extremely careful.
*
* This is not complete. More states could be added.
* For any missing state don't attempt recovery.
*/
#define dirty (1UL << PG_dirty)
#define sc (1UL << PG_swapcache)
#define unevict (1UL << PG_unevictable)
#define mlock (1UL << PG_mlocked)
#define writeback (1UL << PG_writeback)
#define lru (1UL << PG_lru)
#define swapbacked (1UL << PG_swapbacked)
#define head (1UL << PG_head)
#define tail (1UL << PG_tail)
#define compound (1UL << PG_compound)
#define slab (1UL << PG_slab)
#define reserved (1UL << PG_reserved)
static struct page_state {
unsigned long mask;
unsigned long res;
enum mf_action_page_type type;
int (*action)(struct page *p, unsigned long pfn);
} error_states[] = {
{ reserved, reserved, MF_MSG_KERNEL, me_kernel },
/*
* free pages are specially detected outside this table:
* PG_buddy pages only make a small fraction of all free pages.
*/
/*
* Could in theory check if slab page is free or if we can drop
* currently unused objects without touching them. But just
* treat it as standard kernel for now.
*/
{ slab, slab, MF_MSG_SLAB, me_kernel },
#ifdef CONFIG_PAGEFLAGS_EXTENDED
{ head, head, MF_MSG_HUGE, me_huge_page },
{ tail, tail, MF_MSG_HUGE, me_huge_page },
#else
{ compound, compound, MF_MSG_HUGE, me_huge_page },
#endif
{ sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty },
{ sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean },
{ mlock|dirty, mlock|dirty, MF_MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty },
{ mlock|dirty, mlock, MF_MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean },
{ unevict|dirty, unevict|dirty, MF_MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty },
{ unevict|dirty, unevict, MF_MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean },
{ lru|dirty, lru|dirty, MF_MSG_DIRTY_LRU, me_pagecache_dirty },
{ lru|dirty, lru, MF_MSG_CLEAN_LRU, me_pagecache_clean },
/*
* Catchall entry: must be at end.
*/
{ 0, 0, MF_MSG_UNKNOWN, me_unknown },
};
#undef dirty
#undef sc
#undef unevict
#undef mlock
#undef writeback
#undef lru
#undef swapbacked
#undef head
#undef tail
#undef compound
#undef slab
#undef reserved
/*
* "Dirty/Clean" indication is not 100% accurate due to the possibility of
* setting PG_dirty outside page lock. See also comment above set_page_dirty().
*/
static void action_result(unsigned long pfn, enum mf_action_page_type type,
enum mf_result result)
{
trace_memory_failure_event(pfn, type, result);
pr_err("MCE %#lx: recovery action for %s: %s\n",
pfn, action_page_types[type], action_name[result]);
}
static int page_action(struct page_state *ps, struct page *p,
unsigned long pfn)
{
int result;
int count;
result = ps->action(p, pfn);
count = page_count(p) - 1;
if (ps->action == me_swapcache_dirty && result == MF_DELAYED)
count--;
if (count != 0) {
printk(KERN_ERR
"MCE %#lx: %s still referenced by %d users\n",
pfn, action_page_types[ps->type], count);
result = MF_FAILED;
}
action_result(pfn, ps->type, result);
/* Could do more checks here if page looks ok */
/*
* Could adjust zone counters here to correct for the missing page.
*/
return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
}
/**
* get_hwpoison_page() - Get refcount for memory error handling:
* @page: raw error page (hit by memory error)
*
* Return: return 0 if failed to grab the refcount, otherwise true (some
* non-zero value.)
*/
int get_hwpoison_page(struct page *page)
{
struct page *head = compound_head(page);
if (PageHuge(head))
return get_page_unless_zero(head);
/*
* Thp tail page has special refcounting rule (refcount of tail pages
* is stored in ->_mapcount,) so we can't call get_page_unless_zero()
* directly for tail pages.
*/
if (PageTransHuge(head)) {
/*
* Non anonymous thp exists only in allocation/free time. We
* can't handle such a case correctly, so let's give it up.
* This should be better than triggering BUG_ON when kernel
* tries to touch the "partially handled" page.
*/
if (!PageAnon(head)) {
pr_err("MCE: %#lx: non anonymous thp\n",
page_to_pfn(page));
return 0;
}
if (get_page_unless_zero(head)) {
if (PageTail(page))
get_page(page);
return 1;
} else {
return 0;
}
}
return get_page_unless_zero(page);
}
EXPORT_SYMBOL_GPL(get_hwpoison_page);
/*
* Do all that is necessary to remove user space mappings. Unmap
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
int trapno, int flags, struct page **hpagep)
{
enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
LIST_HEAD(tokill);
int ret;
int kill = 1, forcekill;
struct page *hpage = *hpagep;
/*
* Here we are interested only in user-mapped pages, so skip any
* other types of pages.
*/
if (PageReserved(p) || PageSlab(p))
return SWAP_SUCCESS;
if (!(PageLRU(hpage) || PageHuge(p)))
return SWAP_SUCCESS;
/*
* This check implies we don't kill processes if their pages
* are in the swap cache early. Those are always late kills.
*/
if (!page_mapped(hpage))
return SWAP_SUCCESS;
if (PageKsm(p)) {
pr_err("MCE %#lx: can't handle KSM pages.\n", pfn);
return SWAP_FAIL;
}
if (PageSwapCache(p)) {
printk(KERN_ERR
"MCE %#lx: keeping poisoned page in swap cache\n", pfn);
ttu |= TTU_IGNORE_HWPOISON;
}
/*
* Propagate the dirty bit from PTEs to struct page first, because we
* need this to decide if we should kill or just drop the page.
* XXX: the dirty test could be racy: set_page_dirty() may not always
* be called inside page lock (it's recommended but not enforced).
*/
mapping = page_mapping(hpage);
if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
mapping_cap_writeback_dirty(mapping)) {
if (page_mkclean(hpage)) {
SetPageDirty(hpage);
} else {
kill = 0;
ttu |= TTU_IGNORE_HWPOISON;
printk(KERN_INFO
"MCE %#lx: corrupted page was clean: dropped without side effects\n",
pfn);
}
}
/*
* First collect all the processes that have the page
* mapped in dirty form. This has to be done before try_to_unmap,
* because ttu takes the rmap data structures down.
*
* Error handling: We ignore errors here because
* there's nothing that can be done.
*/
if (kill)
collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);
ret = try_to_unmap(hpage, ttu);
if (ret != SWAP_SUCCESS)
printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
pfn, page_mapcount(hpage));
/*
* Now that the dirty bit has been propagated to the
* struct page and all unmaps done we can decide if
* killing is needed or not. Only kill when the page
* was dirty or the process is not restartable,
* otherwise the tokill list is merely
* freed. When there was a problem unmapping earlier
* use a more force-full uncatchable kill to prevent
* any accesses to the poisoned memory.
*/
forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL);
kill_procs(&tokill, forcekill, trapno,
ret != SWAP_SUCCESS, p, pfn, flags);
return ret;
}
static void set_page_hwpoison_huge_page(struct page *hpage)
{
int i;
int nr_pages = 1 << compound_order(hpage);
for (i = 0; i < nr_pages; i++)
SetPageHWPoison(hpage + i);
}
static void clear_page_hwpoison_huge_page(struct page *hpage)
{
int i;
int nr_pages = 1 << compound_order(hpage);
for (i = 0; i < nr_pages; i++)
ClearPageHWPoison(hpage + i);
}
/**
* memory_failure - Handle memory failure of a page.
* @pfn: Page Number of the corrupted page
* @trapno: Trap number reported in the signal to user space.
* @flags: fine tune action taken
*
* This function is called by the low level machine check code
* of an architecture when it detects hardware memory corruption
* of a page. It tries its best to recover, which includes
* dropping pages, killing processes etc.
*
* The function is primarily of use for corruptions that
* happen outside the current execution context (e.g. when
* detected by a background scrubber)
*
* Must run in process context (e.g. a work queue) with interrupts
* enabled and no spinlocks hold.
*/
int memory_failure(unsigned long pfn, int trapno, int flags)
{
struct page_state *ps;
struct page *p;
struct page *hpage;
struct page *orig_head;
int res;
unsigned int nr_pages;
unsigned long page_flags;
if (!sysctl_memory_failure_recovery)
panic("Memory failure from trap %d on page %lx", trapno, pfn);
if (!pfn_valid(pfn)) {
printk(KERN_ERR
"MCE %#lx: memory outside kernel control\n",
pfn);
return -ENXIO;
}
p = pfn_to_page(pfn);
orig_head = hpage = compound_head(p);
if (TestSetPageHWPoison(p)) {
printk(KERN_ERR "MCE %#lx: already hardware poisoned\n", pfn);
return 0;
}
/*
* Currently errors on hugetlbfs pages are measured in hugepage units,
* so nr_pages should be 1 << compound_order. OTOH when errors are on
* transparent hugepages, they are supposed to be split and error
* measurement is done in normal page units. So nr_pages should be one
* in this case.
*/
if (PageHuge(p))
nr_pages = 1 << compound_order(hpage);
else /* normal page or thp */
nr_pages = 1;
atomic_long_add(nr_pages, &num_poisoned_pages);
/*
* 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 a free hugepage, which is also safe:
* an affected hugepage will be dequeued from hugepage freelist,
* so there's no concern about reusing it ever after.
* 3) 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.
*/
if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p)) {
if (is_free_buddy_page(p)) {
action_result(pfn, MF_MSG_BUDDY, MF_DELAYED);
return 0;
} else if (PageHuge(hpage)) {
/*
* Check "filter hit" and "race with other subpage."
*/
lock_page(hpage);
if (PageHWPoison(hpage)) {
if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
|| (p != hpage && TestSetPageHWPoison(hpage))) {
atomic_long_sub(nr_pages, &num_poisoned_pages);
unlock_page(hpage);
return 0;
}
}
set_page_hwpoison_huge_page(hpage);
res = dequeue_hwpoisoned_huge_page(hpage);
action_result(pfn, MF_MSG_FREE_HUGE,
res ? MF_IGNORED : MF_DELAYED);
unlock_page(hpage);
return res;
} else {
action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
return -EBUSY;
}
}
if (!PageHuge(p) && PageTransHuge(hpage)) {
if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
if (!PageAnon(hpage))
pr_err("MCE: %#lx: non anonymous thp\n", pfn);
else
pr_err("MCE: %#lx: thp split failed\n", pfn);
if (TestClearPageHWPoison(p))
atomic_long_sub(nr_pages, &num_poisoned_pages);
put_page(p);
if (p != hpage)
put_page(hpage);
return -EBUSY;
}
VM_BUG_ON_PAGE(!page_count(p), p);
hpage = compound_head(p);
}
/*
* We ignore non-LRU pages for good reasons.
* - PG_locked is only well defined for LRU pages and a few others
* - to avoid races with __set_page_locked()
* - to avoid races with __SetPageSlab*() (and more non-atomic ops)
* The check (unnecessarily) ignores LRU pages being isolated and
* walked by the page reclaim code, however that's not a big loss.
*/
if (!PageHuge(p)) {
if (!PageLRU(p))
shake_page(p, 0);
if (!PageLRU(p)) {
/*
* shake_page could have turned it free.
*/
if (is_free_buddy_page(p)) {
if (flags & MF_COUNT_INCREASED)
action_result(pfn, MF_MSG_BUDDY, MF_DELAYED);
else
action_result(pfn, MF_MSG_BUDDY_2ND,
MF_DELAYED);
return 0;
}
}
}
lock_page(hpage);
/*
* The page could have changed compound pages during the locking.
* If this happens just bail out.
*/
if (PageCompound(p) && compound_head(p) != orig_head) {
action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED);
res = -EBUSY;
goto out;
}
/*
* We use page flags to determine what action should be taken, but
* the flags can be modified by the error containment action. One
* example is an mlocked page, where PG_mlocked is cleared by
* page_remove_rmap() in try_to_unmap_one(). So to determine page status
* correctly, we save a copy of the page flags at this time.
*/
page_flags = p->flags;
/*
* unpoison always clear PG_hwpoison inside page lock
*/
if (!PageHWPoison(p)) {
printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
atomic_long_sub(nr_pages, &num_poisoned_pages);
unlock_page(hpage);
put_page(hpage);
return 0;
}
if (hwpoison_filter(p)) {
if (TestClearPageHWPoison(p))
atomic_long_sub(nr_pages, &num_poisoned_pages);
unlock_page(hpage);
put_page(hpage);
return 0;
}
if (!PageHuge(p) && !PageTransTail(p) && !PageLRU(p))
goto identify_page_state;
/*
* For error on the tail page, we should set PG_hwpoison
* on the head page to show that the hugepage is hwpoisoned
*/
if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) {
action_result(pfn, MF_MSG_POISONED_HUGE, MF_IGNORED);
unlock_page(hpage);
put_page(hpage);
return 0;
}
/*
* Set PG_hwpoison on all pages in an error hugepage,
* because containment is done in hugepage unit for now.
* Since we have done TestSetPageHWPoison() for the head page with
* page lock held, we can safely set PG_hwpoison bits on tail pages.
*/
if (PageHuge(p))
set_page_hwpoison_huge_page(hpage);
/*
* It's very difficult to mess with pages currently under IO
* and in many cases impossible, so we just avoid it here.
*/
wait_on_page_writeback(p);
/*
* Now take care of user space mappings.
* Abort on fail: __delete_from_page_cache() assumes unmapped page.
*
* When the raw error page is thp tail page, hpage points to the raw
* page after thp split.
*/
if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
!= SWAP_SUCCESS) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
goto out;
}
/*
* Torn down by someone else?
*/
if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED);
res = -EBUSY;
goto out;
}
identify_page_state:
res = -EBUSY;
/*
* The first check uses the current page flags which may not have any
* relevant information. The second check with the saved page flagss is
* carried out only if the first check can't determine the page status.
*/
for (ps = error_states;; ps++)
if ((p->flags & ps->mask) == ps->res)
break;
page_flags |= (p->flags & (1UL << PG_dirty));
if (!ps->mask)
for (ps = error_states;; ps++)
if ((page_flags & ps->mask) == ps->res)
break;
res = page_action(ps, p, pfn);
out:
unlock_page(hpage);
return res;
}
EXPORT_SYMBOL_GPL(memory_failure);
#define MEMORY_FAILURE_FIFO_ORDER 4
#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER)
struct memory_failure_entry {
unsigned long pfn;
int trapno;
int flags;
};
struct memory_failure_cpu {
DECLARE_KFIFO(fifo, struct memory_failure_entry,
MEMORY_FAILURE_FIFO_SIZE);
spinlock_t lock;
struct work_struct work;
};
static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu);
/**
* memory_failure_queue - Schedule handling memory failure of a page.
* @pfn: Page Number of the corrupted page
* @trapno: Trap number reported in the signal to user space.
* @flags: Flags for memory failure handling
*
* This function is called by the low level hardware error handler
* when it detects hardware memory corruption of a page. It schedules
* the recovering of error page, including dropping pages, killing
* processes etc.
*
* The function is primarily of use for corruptions that
* happen outside the current execution context (e.g. when
* detected by a background scrubber)
*
* Can run in IRQ context.
*/
void memory_failure_queue(unsigned long pfn, int trapno, int flags)
{
struct memory_failure_cpu *mf_cpu;
unsigned long proc_flags;
struct memory_failure_entry entry = {
.pfn = pfn,
.trapno = trapno,
.flags = flags,
};
mf_cpu = &get_cpu_var(memory_failure_cpu);
spin_lock_irqsave(&mf_cpu->lock, proc_flags);
if (kfifo_put(&mf_cpu->fifo, entry))
schedule_work_on(smp_processor_id(), &mf_cpu->work);
else
pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n",
pfn);
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
put_cpu_var(memory_failure_cpu);
}
EXPORT_SYMBOL_GPL(memory_failure_queue);
static void memory_failure_work_func(struct work_struct *work)
{
struct memory_failure_cpu *mf_cpu;
struct memory_failure_entry entry = { 0, };
unsigned long proc_flags;
int gotten;
mf_cpu = this_cpu_ptr(&memory_failure_cpu);
for (;;) {
spin_lock_irqsave(&mf_cpu->lock, proc_flags);
gotten = kfifo_get(&mf_cpu->fifo, &entry);
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
if (!gotten)
break;
if (entry.flags & MF_SOFT_OFFLINE)
soft_offline_page(pfn_to_page(entry.pfn), entry.flags);
else
memory_failure(entry.pfn, entry.trapno, entry.flags);
}
}
static int __init memory_failure_init(void)
{
struct memory_failure_cpu *mf_cpu;
int cpu;
for_each_possible_cpu(cpu) {
mf_cpu = &per_cpu(memory_failure_cpu, cpu);
spin_lock_init(&mf_cpu->lock);
INIT_KFIFO(mf_cpu->fifo);
INIT_WORK(&mf_cpu->work, memory_failure_work_func);
}
return 0;
}
core_initcall(memory_failure_init);
/**
* unpoison_memory - Unpoison a previously poisoned page
* @pfn: Page number of the to be unpoisoned page
*
* Software-unpoison a page that has been poisoned by
* memory_failure() earlier.
*
* This is only done on the software-level, so it only works
* for linux injected failures, not real hardware failures
*
* Returns 0 for success, otherwise -errno.
*/
int unpoison_memory(unsigned long pfn)
{
struct page *page;
struct page *p;
int freeit = 0;
unsigned int nr_pages;
if (!pfn_valid(pfn))
return -ENXIO;
p = pfn_to_page(pfn);
page = compound_head(p);
if (!PageHWPoison(p)) {
pr_info("MCE: Page was already unpoisoned %#lx\n", pfn);
return 0;
}
/*
* unpoison_memory() can encounter thp only when the thp is being
* worked by memory_failure() and the page lock is not held yet.
* In such case, we yield to memory_failure() and make unpoison fail.
*/
if (!PageHuge(page) && PageTransHuge(page)) {
pr_info("MCE: Memory failure is now running on %#lx\n", pfn);
return 0;
}
nr_pages = 1 << compound_order(page);
if (!get_hwpoison_page(p)) {
/*
* Since HWPoisoned hugepage should have non-zero refcount,
* race between memory failure and unpoison seems to happen.
* In such case unpoison fails and memory failure runs
* to the end.
*/
if (PageHuge(page)) {
pr_info("MCE: Memory failure is now running on free hugepage %#lx\n", pfn);
return 0;
}
if (TestClearPageHWPoison(p))
atomic_long_dec(&num_poisoned_pages);
pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
return 0;
}
lock_page(page);
/*
* This test is racy because PG_hwpoison is set outside of page lock.
* That's acceptable because that won't trigger kernel panic. Instead,
* the PG_hwpoison page will be caught and isolated on the entrance to
* the free buddy page pool.
*/
if (TestClearPageHWPoison(page)) {
pr_info("MCE: Software-unpoisoned page %#lx\n", pfn);
atomic_long_sub(nr_pages, &num_poisoned_pages);
freeit = 1;
if (PageHuge(page))
clear_page_hwpoison_huge_page(page);
}
unlock_page(page);
put_page(page);
if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
put_page(page);
return 0;
}
EXPORT_SYMBOL(unpoison_memory);
static struct page *new_page(struct page *p, unsigned long private, int **x)
{
int nid = page_to_nid(p);
if (PageHuge(p))
return alloc_huge_page_node(page_hstate(compound_head(p)),
nid);
else
return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
}
/*
* Safely get reference count of an arbitrary page.
* Returns 0 for a free page, -EIO for a zero refcount page
* that is not free, and 1 for any other page type.
* For 1 the page is returned with increased page count, otherwise not.
*/
static int __get_any_page(struct page *p, unsigned long pfn, int flags)
{
int ret;
if (flags & MF_COUNT_INCREASED)
return 1;
/*
* When the target page is a free hugepage, just remove it
* from free hugepage list.
*/
if (!get_hwpoison_page(p)) {
if (PageHuge(p)) {
pr_info("%s: %#lx free huge page\n", __func__, pfn);
ret = 0;
} else if (is_free_buddy_page(p)) {
pr_info("%s: %#lx free buddy page\n", __func__, pfn);
ret = 0;
} else {
pr_info("%s: %#lx: unknown zero refcount page type %lx\n",
__func__, pfn, p->flags);
ret = -EIO;
}
} else {
/* Not a free page */
ret = 1;
}
return ret;
}
static int get_any_page(struct page *page, unsigned long pfn, int flags)
{
int ret = __get_any_page(page, pfn, flags);
if (ret == 1 && !PageHuge(page) && !PageLRU(page)) {
/*
* Try to free it.
*/
put_page(page);
shake_page(page, 1);
/*
* Did it turn free?
*/
ret = __get_any_page(page, pfn, 0);
if (!PageLRU(page)) {
/* Drop page reference which is from __get_any_page() */
put_page(page);
pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
pfn, page->flags);
return -EIO;
}
}
return ret;
}
static int soft_offline_huge_page(struct page *page, int flags)
{
int ret;
unsigned long pfn = page_to_pfn(page);
struct page *hpage = compound_head(page);
LIST_HEAD(pagelist);
/*
* This double-check of PageHWPoison is to avoid the race with
* memory_failure(). See also comment in __soft_offline_page().
*/
lock_page(hpage);
if (PageHWPoison(hpage)) {
unlock_page(hpage);
put_page(hpage);
pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
return -EBUSY;
}
unlock_page(hpage);
ret = isolate_huge_page(hpage, &pagelist);
/*
* get_any_page() and isolate_huge_page() takes a refcount each,
* so need to drop one here.
*/
put_page(hpage);
if (!ret) {
pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
return -EBUSY;
}
ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (ret) {
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
pfn, ret, page->flags);
/*
* We know that soft_offline_huge_page() tries to migrate
* only one hugepage pointed to by hpage, so we need not
* run through the pagelist here.
*/
putback_active_hugepage(hpage);
if (ret > 0)
ret = -EIO;
} else {
/* overcommit hugetlb page will be freed to buddy */
if (PageHuge(page)) {
set_page_hwpoison_huge_page(hpage);
dequeue_hwpoisoned_huge_page(hpage);
atomic_long_add(1 << compound_order(hpage),
&num_poisoned_pages);
} else {
SetPageHWPoison(page);
atomic_long_inc(&num_poisoned_pages);
}
}
return ret;
}
static int __soft_offline_page(struct page *page, int flags)
{
int ret;
unsigned long pfn = page_to_pfn(page);
/*
* Check PageHWPoison again inside page lock because PageHWPoison
* is set by memory_failure() outside page lock. Note that
* memory_failure() also double-checks PageHWPoison inside page lock,
* so there's no race between soft_offline_page() and memory_failure().
*/
lock_page(page);
wait_on_page_writeback(page);
if (PageHWPoison(page)) {
unlock_page(page);
put_page(page);
pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
}
/*
* Try to invalidate first. This should work for
* non dirty unmapped page cache pages.
*/
ret = invalidate_inode_page(page);
unlock_page(page);
/*
* RED-PEN would be better to keep it isolated here, but we
* would need to fix isolation locking first.
*/
if (ret == 1) {
put_page(page);
pr_info("soft_offline: %#lx: invalidated\n", pfn);
SetPageHWPoison(page);
atomic_long_inc(&num_poisoned_pages);
return 0;
}
/*
* Simple invalidation didn't work.
* Try to migrate to a new page instead. migrate.c
* handles a large number of cases for us.
*/
ret = isolate_lru_page(page);
/*
* Drop page reference which is came from get_any_page()
* successful isolate_lru_page() already took another one.
*/
put_page(page);
if (!ret) {
LIST_HEAD(pagelist);
inc_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
list_add(&page->lru, &pagelist);
if (!TestSetPageHWPoison(page))
atomic_long_inc(&num_poisoned_pages);
ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (ret) {
if (!list_empty(&pagelist)) {
list_del(&page->lru);
dec_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
putback_lru_page(page);
}
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
pfn, ret, page->flags);
if (ret > 0)
ret = -EIO;
if (TestClearPageHWPoison(page))
atomic_long_dec(&num_poisoned_pages);
}
} else {
pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
pfn, ret, page_count(page), page->flags);
}
return ret;
}
/**
* soft_offline_page - Soft offline a page.
* @page: page to offline
* @flags: flags. Same as memory_failure().
*
* Returns 0 on success, otherwise negated errno.
*
* Soft offline a page, by migration or invalidation,
* without killing anything. This is for the case when
* a page is not corrupted yet (so it's still valid to access),
* but has had a number of corrected errors and is better taken
* out.
*
* The actual policy on when to do that is maintained by
* user space.
*
* This should never impact any application or cause data loss,
* however it might take some time.
*
* This is not a 100% solution for all memory, but tries to be
* ``good enough'' for the majority of memory.
*/
int soft_offline_page(struct page *page, int flags)
{
int ret;
unsigned long pfn = page_to_pfn(page);
struct page *hpage = compound_head(page);
if (PageHWPoison(page)) {
pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
}
if (!PageHuge(page) && PageTransHuge(hpage)) {
if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
pr_info("soft offline: %#lx: failed to split THP\n",
pfn);
return -EBUSY;
}
}
get_online_mems();
ret = get_any_page(page, pfn, flags);
put_online_mems();
if (ret > 0) { /* for in-use pages */
if (PageHuge(page))
ret = soft_offline_huge_page(page, flags);
else
ret = __soft_offline_page(page, flags);
} else if (ret == 0) { /* for free pages */
if (PageHuge(page)) {
set_page_hwpoison_huge_page(hpage);
if (!dequeue_hwpoisoned_huge_page(hpage))
atomic_long_add(1 << compound_order(hpage),
&num_poisoned_pages);
} else {
if (!TestSetPageHWPoison(page))
atomic_long_inc(&num_poisoned_pages);
}
}
return ret;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/memory.c
/*
* linux/mm/memory.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* demand-loading started 01.12.91 - seems it is high on the list of
* things wanted, and it should be easy to implement. - Linus
*/
/*
* Ok, demand-loading was easy, shared pages a little bit tricker. Shared
* pages started 02.12.91, seems to work. - Linus.
*
* Tested sharing by executing about 30 /bin/sh: under the old kernel it
* would have taken more than the 6M I have free, but it worked well as
* far as I could see.
*
* Also corrected some "invalidate()"s - I wasn't doing enough of them.
*/
/*
* Real VM (paging to/from disk) started 18.12.91. Much more work and
* thought has to go into this. Oh, well..
* 19.12.91 - works, somewhat. Sometimes I get faults, don't know why.
* Found it. Everything seems to work now.
* 20.12.91 - Ok, making the swap-device changeable like the root.
*/
/*
* 05.04.94 - Multi-page memory management added for v1.1.
* Idea by Alex Bligh (alex@cconcepts.co.uk)
*
* 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG
* (Gerhard.Wichert@pdb.siemens.de)
*
* Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
*/
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/export.h>
#include <linux/delayacct.h>
#include <linux/init.h>
#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/kallsyms.h>
#include <linux/swapops.h>
#include <linux/elf.h>
#include <linux/gfp.h>
#include <linux/migrate.h>
#include <linux/string.h>
#include <linux/dma-debug.h>
#include <linux/debugfs.h>
#include <asm/io.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
#include "internal.h"
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif
#ifndef CONFIG_NEED_MULTIPLE_NODES
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;
EXPORT_SYMBOL(max_mapnr);
EXPORT_SYMBOL(mem_map);
#endif
/*
* A number of key systems in x86 including ioremap() rely on the assumption
* that high_memory defines the upper bound on direct map memory, then end
* of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and
* highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
* and ZONE_HIGHMEM.
*/
void * high_memory;
EXPORT_SYMBOL(high_memory);
/*
* Randomize the address space (stacks, mmaps, brk, etc.).
*
* ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization,
* as ancient (libc5 based) binaries can segfault. )
*/
int randomize_va_space __read_mostly =
#ifdef CONFIG_COMPAT_BRK
1;
#else
2;
#endif
static int __init disable_randmaps(char *s)
{
randomize_va_space = 0;
return 1;
}
__setup("norandmaps", disable_randmaps);
unsigned long zero_pfn __read_mostly;
unsigned long highest_memmap_pfn __read_mostly;
EXPORT_SYMBOL(zero_pfn);
/*
* CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
*/
static int __init init_zero_pfn(void)
{
zero_pfn = page_to_pfn(ZERO_PAGE(0));
return 0;
}
core_initcall(init_zero_pfn);
#if defined(SPLIT_RSS_COUNTING)
void sync_mm_rss(struct mm_struct *mm)
{
int i;
for (i = 0; i < NR_MM_COUNTERS; i++) {
if (current->rss_stat.count[i]) {
add_mm_counter(mm, i, current->rss_stat.count[i]);
current->rss_stat.count[i] = 0;
}
}
current->rss_stat.events = 0;
}
static void add_mm_counter_fast(struct mm_struct *mm, int member, int val)
{
struct task_struct *task = current;
if (likely(task->mm == mm))
task->rss_stat.count[member] += val;
else
add_mm_counter(mm, member, val);
}
#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1)
#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1)
/* sync counter once per 64 page faults */
#define TASK_RSS_EVENTS_THRESH (64)
static void check_sync_rss_stat(struct task_struct *task)
{
if (unlikely(task != current))
return;
if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH))
sync_mm_rss(task->mm);
}
#else /* SPLIT_RSS_COUNTING */
#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)
static void check_sync_rss_stat(struct task_struct *task)
{
}
#endif /* SPLIT_RSS_COUNTING */
#ifdef HAVE_GENERIC_MMU_GATHER
static int tlb_next_batch(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch;
batch = tlb->active;
if (batch->next) {
tlb->active = batch->next;
return 1;
}
if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
return 0;
batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
if (!batch)
return 0;
tlb->batch_count++;
batch->next = NULL;
batch->nr = 0;
batch->max = MAX_GATHER_BATCH;
tlb->active->next = batch;
tlb->active = batch;
return 1;
}
/* tlb_gather_mmu
* Called to initialize an (on-stack) mmu_gather structure for page-table
* tear-down from @mm. The @fullmm argument is used when @mm is without
* users and we're going to destroy the full address space (exit/execve).
*/
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
/* Is it from 0 to ~0? */
tlb->fullmm = !(start | (end+1));
tlb->need_flush_all = 0;
tlb->local.next = NULL;
tlb->local.nr = 0;
tlb->local.max = ARRAY_SIZE(tlb->__pages);
tlb->active = &tlb->local;
tlb->batch_count = 0;
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
tlb->batch = NULL;
#endif
__tlb_reset_range(tlb);
}
static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
if (!tlb->end)
return;
tlb_flush(tlb);
mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
tlb_table_flush(tlb);
#endif
__tlb_reset_range(tlb);
}
static void tlb_flush_mmu_free(struct mmu_gather *tlb)
{
struct mmu_gather_batch *batch;
for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
free_pages_and_swap_cache(batch->pages, batch->nr);
batch->nr = 0;
}
tlb->active = &tlb->local;
}
void tlb_flush_mmu(struct mmu_gather *tlb)
{
tlb_flush_mmu_tlbonly(tlb);
tlb_flush_mmu_free(tlb);
}
/* tlb_finish_mmu
* Called at the end of the shootdown operation to free up any resources
* that were required.
*/
void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
{
struct mmu_gather_batch *batch, *next;
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
check_pgt_cache();
for (batch = tlb->local.next; batch; batch = next) {
next = batch->next;
free_pages((unsigned long)batch, 0);
}
tlb->local.next = NULL;
}
/* __tlb_remove_page
* Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
* handling the additional races in SMP caused by other CPUs caching valid
* mappings in their TLBs. Returns the number of free page slots left.
* When out of page slots we must call tlb_flush_mmu().
*/
int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
struct mmu_gather_batch *batch;
VM_BUG_ON(!tlb->end);
batch = tlb->active;
batch->pages[batch->nr++] = page;
if (batch->nr == batch->max) {
if (!tlb_next_batch(tlb))
return 0;
batch = tlb->active;
}
VM_BUG_ON_PAGE(batch->nr > batch->max, page);
return batch->max - batch->nr;
}
#endif /* HAVE_GENERIC_MMU_GATHER */
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
/*
* See the comment near struct mmu_table_batch.
*/
static void tlb_remove_table_smp_sync(void *arg)
{
/* Simply deliver the interrupt */
}
static void tlb_remove_table_one(void *table)
{
/*
* This isn't an RCU grace period and hence the page-tables cannot be
* assumed to be actually RCU-freed.
*
* It is however sufficient for software page-table walkers that rely on
* IRQ disabling. See the comment near struct mmu_table_batch.
*/
smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
__tlb_remove_table(table);
}
static void tlb_remove_table_rcu(struct rcu_head *head)
{
struct mmu_table_batch *batch;
int i;
batch = container_of(head, struct mmu_table_batch, rcu);
for (i = 0; i < batch->nr; i++)
__tlb_remove_table(batch->tables[i]);
free_page((unsigned long)batch);
}
void tlb_table_flush(struct mmu_gather *tlb)
{
struct mmu_table_batch **batch = &tlb->batch;
if (*batch) {
call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
*batch = NULL;
}
}
void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
struct mmu_table_batch **batch = &tlb->batch;
/*
* When there's less then two users of this mm there cannot be a
* concurrent page-table walk.
*/
if (atomic_read(&tlb->mm->mm_users) < 2) {
__tlb_remove_table(table);
return;
}
if (*batch == NULL) {
*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
if (*batch == NULL) {
tlb_remove_table_one(table);
return;
}
(*batch)->nr = 0;
}
(*batch)->tables[(*batch)->nr++] = table;
if ((*batch)->nr == MAX_TABLE_BATCH)
tlb_table_flush(tlb);
}
#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
/*
* Note: this doesn't free the actual pages themselves. That
* has been handled earlier when unmapping all the memory regions.
*/
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
unsigned long addr)
{
pgtable_t token = pmd_pgtable(*pmd);
pmd_clear(pmd);
pte_free_tlb(tlb, token, addr);
atomic_long_dec(&tlb->mm->nr_ptes);
}
static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pmd_t *pmd;
unsigned long next;
unsigned long start;
start = addr;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
free_pte_range(tlb, pmd, addr);
} while (pmd++, addr = next, addr != end);
start &= PUD_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PUD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
pmd = pmd_offset(pud, start);
pud_clear(pud);
pmd_free_tlb(tlb, pmd, start);
mm_dec_nr_pmds(tlb->mm);
}
static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pud_t *pud;
unsigned long next;
unsigned long start;
start = addr;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
free_pmd_range(tlb, pud, addr, next, floor, ceiling);
} while (pud++, addr = next, addr != end);
start &= PGDIR_MASK;
if (start < floor)
return;
if (ceiling) {
ceiling &= PGDIR_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
return;
pud = pud_offset(pgd, start);
pgd_clear(pgd);
pud_free_tlb(tlb, pud, start);
}
/*
* This function frees user-level page tables of a process.
*/
void free_pgd_range(struct mmu_gather *tlb,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
unsigned long next;
/*
* The next few lines have given us lots of grief...
*
* Why are we testing PMD* at this top level? Because often
* there will be no work to do at all, and we'd prefer not to
* go all the way down to the bottom just to discover that.
*
* Why all these "- 1"s? Because 0 represents both the bottom
* of the address space and the top of it (using -1 for the
* top wouldn't help much: the masks would do the wrong thing).
* The rule is that addr 0 and floor 0 refer to the bottom of
* the address space, but end 0 and ceiling 0 refer to the top
* Comparisons need to use "end - 1" and "ceiling - 1" (though
* that end 0 case should be mythical).
*
* Wherever addr is brought up or ceiling brought down, we must
* be careful to reject "the opposite 0" before it confuses the
* subsequent tests. But what about where end is brought down
* by PMD_SIZE below? no, end can't go down to 0 there.
*
* Whereas we round start (addr) and ceiling down, by different
* masks at different levels, in order to test whether a table
* now has no other vmas using it, so can be freed, we don't
* bother to round floor or end up - the tests don't need that.
*/
addr &= PMD_MASK;
if (addr < floor) {
addr += PMD_SIZE;
if (!addr)
return;
}
if (ceiling) {
ceiling &= PMD_MASK;
if (!ceiling)
return;
}
if (end - 1 > ceiling - 1)
end -= PMD_SIZE;
if (addr > end - 1)
return;
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
free_pud_range(tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
}
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long floor, unsigned long ceiling)
{
while (vma) {
struct vm_area_struct *next = vma->vm_next;
unsigned long addr = vma->vm_start;
/*
* Hide vma from rmap and truncate_pagecache before freeing
* pgtables
*/
unlink_anon_vmas(vma);
unlink_file_vma(vma);
if (is_vm_hugetlb_page(vma)) {
hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
floor, next? next->vm_start: ceiling);
} else {
/*
* Optimization: gather nearby vmas into one call down
*/
while (next && next->vm_start <= vma->vm_end + PMD_SIZE
&& !is_vm_hugetlb_page(next)) {
vma = next;
next = vma->vm_next;
unlink_anon_vmas(vma);
unlink_file_vma(vma);
}
free_pgd_range(tlb, addr, vma->vm_end,
floor, next? next->vm_start: ceiling);
}
vma = next;
}
}
int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long address)
{
spinlock_t *ptl;
pgtable_t new = pte_alloc_one(mm, address);
int wait_split_huge_page;
if (!new)
return -ENOMEM;
/*
* Ensure all pte setup (eg. pte page lock and page clearing) are
* visible before the pte is made visible to other CPUs by being
* put into page tables.
*
* The other side of the story is the pointer chasing in the page
* table walking code (when walking the page table without locking;
* ie. most of the time). Fortunately, these data accesses consist
* of a chain of data-dependent loads, meaning most CPUs (alpha
* being the notable exception) will already guarantee loads are
* seen in-order. See the alpha page table accessors for the
* smp_read_barrier_depends() barriers in page table walking code.
*/
smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
ptl = pmd_lock(mm, pmd);
wait_split_huge_page = 0;
if (likely(pmd_none(*pmd))) { /* Has another populated it ? */
atomic_long_inc(&mm->nr_ptes);
pmd_populate(mm, pmd, new);
new = NULL;
} else if (unlikely(pmd_trans_splitting(*pmd)))
wait_split_huge_page = 1;
spin_unlock(ptl);
if (new)
pte_free(mm, new);
if (wait_split_huge_page)
wait_split_huge_page(vma->anon_vma, pmd);
return 0;
}
int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
{
pte_t *new = pte_alloc_one_kernel(&init_mm, address);
if (!new)
return -ENOMEM;
smp_wmb(); /* See comment in __pte_alloc */
spin_lock(&init_mm.page_table_lock);
if (likely(pmd_none(*pmd))) { /* Has another populated it ? */
pmd_populate_kernel(&init_mm, pmd, new);
new = NULL;
} else
VM_BUG_ON(pmd_trans_splitting(*pmd));
spin_unlock(&init_mm.page_table_lock);
if (new)
pte_free_kernel(&init_mm, new);
return 0;
}
static inline void init_rss_vec(int *rss)
{
memset(rss, 0, sizeof(int) * NR_MM_COUNTERS);
}
static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss)
{
int i;
if (current->mm == mm)
sync_mm_rss(mm);
for (i = 0; i < NR_MM_COUNTERS; i++)
if (rss[i])
add_mm_counter(mm, i, rss[i]);
}
/*
* This function is called to print an error when a bad pte
* is found. For example, we might have a PFN-mapped pte in
* a region that doesn't allow it.
*
* The calling function must still handle the error.
*/
static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
pte_t pte, struct page *page)
{
pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
pud_t *pud = pud_offset(pgd, addr);
pmd_t *pmd = pmd_offset(pud, addr);
struct address_space *mapping;
pgoff_t index;
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
return;
}
if (nr_unshown) {
printk(KERN_ALERT
"BUG: Bad page map: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
index = linear_page_index(vma, addr);
printk(KERN_ALERT
"BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n",
current->comm,
(long long)pte_val(pte), (long long)pmd_val(*pmd));
if (page)
dump_page(page, "bad pte");
printk(KERN_ALERT
"addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n",
(void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
/*
* Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y
*/
pr_alert("file:%pD fault:%pf mmap:%pf readpage:%pf\n",
vma->vm_file,
vma->vm_ops ? vma->vm_ops->fault : NULL,
vma->vm_file ? vma->vm_file->f_op->mmap : NULL,
mapping ? mapping->a_ops->readpage : NULL);
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
/*
* vm_normal_page -- This function gets the "struct page" associated with a pte.
*
* "Special" mappings do not wish to be associated with a "struct page" (either
* it doesn't exist, or it exists but they don't want to touch it). In this
* case, NULL is returned here. "Normal" mappings do have a struct page.
*
* There are 2 broad cases. Firstly, an architecture may define a pte_special()
* pte bit, in which case this function is trivial. Secondly, an architecture
* may not have a spare pte bit, which requires a more complicated scheme,
* described below.
*
* A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
* special mapping (even if there are underlying and valid "struct pages").
* COWed pages of a VM_PFNMAP are always normal.
*
* The way we recognize COWed pages within VM_PFNMAP mappings is through the
* rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
* set, and the vm_pgoff will point to the first PFN mapped: thus every special
* mapping will always honor the rule
*
* pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
*
* And for normal mappings this is false.
*
* This restricts such mappings to be a linear translation from virtual address
* to pfn. To get around this restriction, we allow arbitrary mappings so long
* as the vma is not a COW mapping; in that case, we know that all ptes are
* special (because none can have been COWed).
*
*
* In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
*
* VM_MIXEDMAP mappings can likewise contain memory with or without "struct
* page" backing, however the difference is that _all_ pages with a struct
* page (that is, those where pfn_valid is true) are refcounted and considered
* normal pages by the VM. The disadvantage is that pages are refcounted
* (which can be slower and simply not an option for some PFNMAP users). The
* advantage is that we don't have to follow the strict linearity rule of
* PFNMAP mappings in order to support COWable mappings.
*
*/
#ifdef __HAVE_ARCH_PTE_SPECIAL
# define HAVE_PTE_SPECIAL 1
#else
# define HAVE_PTE_SPECIAL 0
#endif
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
if (HAVE_PTE_SPECIAL) {
if (likely(!pte_special(pte)))
goto check_pfn;
if (vma->vm_ops && vma->vm_ops->find_special_page)
return vma->vm_ops->find_special_page(vma, addr);
if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
return NULL;
if (!is_zero_pfn(pfn))
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/* !HAVE_PTE_SPECIAL case follows: */
if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
if (vma->vm_flags & VM_MIXEDMAP) {
if (!pfn_valid(pfn))
return NULL;
goto out;
} else {
unsigned long off;
off = (addr - vma->vm_start) >> PAGE_SHIFT;
if (pfn == vma->vm_pgoff + off)
return NULL;
if (!is_cow_mapping(vma->vm_flags))
return NULL;
}
}
if (is_zero_pfn(pfn))
return NULL;
check_pfn:
if (unlikely(pfn > highest_memmap_pfn)) {
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
/*
* NOTE! We still have PageReserved() pages in the page tables.
* eg. VDSO mappings can cause them to exist.
*/
out:
return pfn_to_page(pfn);
}
/*
* copy one vm_area from one task to the other. Assumes the page tables
* already present in the new task to be cleared in the whole range
* covered by this vma.
*/
static inline unsigned long
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
unsigned long addr, int *rss)
{
unsigned long vm_flags = vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
/* pte contains position in swap or file, so copy. */
if (unlikely(!pte_present(pte))) {
swp_entry_t entry = pte_to_swp_entry(pte);
if (likely(!non_swap_entry(entry))) {
if (swap_duplicate(entry) < 0)
return entry.val;
/* make sure dst_mm is on swapoff's mmlist. */
if (unlikely(list_empty(&dst_mm->mmlist))) {
spin_lock(&mmlist_lock);
if (list_empty(&dst_mm->mmlist))
list_add(&dst_mm->mmlist,
&src_mm->mmlist);
spin_unlock(&mmlist_lock);
}
rss[MM_SWAPENTS]++;
} else if (is_migration_entry(entry)) {
page = migration_entry_to_page(entry);
if (PageAnon(page))
rss[MM_ANONPAGES]++;
else
rss[MM_FILEPAGES]++;
if (is_write_migration_entry(entry) &&
is_cow_mapping(vm_flags)) {
/*
* COW mappings require pages in both
* parent and child to be set to read.
*/
make_migration_entry_read(&entry);
pte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(*src_pte))
pte = pte_swp_mksoft_dirty(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
}
goto out_set_pte;
}
/*
* If it's a COW mapping, write protect it both
* in the parent and the child
*/
if (is_cow_mapping(vm_flags)) {
ptep_set_wrprotect(src_mm, addr, src_pte);
pte = pte_wrprotect(pte);
}
/*
* If it's a shared mapping, mark it clean in
* the child
*/
if (vm_flags & VM_SHARED)
pte = pte_mkclean(pte);
pte = pte_mkold(pte);
page = vm_normal_page(vma, addr, pte);
if (page) {
get_page(page);
page_dup_rmap(page);
if (PageAnon(page))
rss[MM_ANONPAGES]++;
else
rss[MM_FILEPAGES]++;
}
out_set_pte:
set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pte_t *orig_src_pte, *orig_dst_pte;
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
int progress = 0;
int rss[NR_MM_COUNTERS];
swp_entry_t entry = (swp_entry_t){0};
again:
init_rss_vec(rss);
dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
if (!dst_pte)
return -ENOMEM;
src_pte = pte_offset_map(src_pmd, addr);
src_ptl = pte_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
orig_src_pte = src_pte;
orig_dst_pte = dst_pte;
arch_enter_lazy_mmu_mode();
do {
/*
* We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU.
*/
if (progress >= 32) {
progress = 0;
if (need_resched() ||
spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
break;
}
if (pte_none(*src_pte)) {
progress++;
continue;
}
entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
vma, addr, rss);
if (entry.val)
break;
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
spin_unlock(src_ptl);
pte_unmap(orig_src_pte);
add_mm_rss_vec(dst_mm, rss);
pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();
if (entry.val) {
if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
return -ENOMEM;
progress = 0;
}
if (addr != end)
goto again;
return 0;
}
static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pmd_t *src_pmd, *dst_pmd;
unsigned long next;
dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
if (!dst_pmd)
return -ENOMEM;
src_pmd = pmd_offset(src_pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*src_pmd)) {
int err;
VM_BUG_ON(next-addr != HPAGE_PMD_SIZE);
err = copy_huge_pmd(dst_mm, src_mm,
dst_pmd, src_pmd, addr, vma);
if (err == -ENOMEM)
return -ENOMEM;
if (!err)
continue;
/* fall through */
}
if (pmd_none_or_clear_bad(src_pmd))
continue;
if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
vma, addr, next))
return -ENOMEM;
} while (dst_pmd++, src_pmd++, addr = next, addr != end);
return 0;
}
static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pud_t *src_pud, *dst_pud;
unsigned long next;
dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
if (!dst_pud)
return -ENOMEM;
src_pud = pud_offset(src_pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(src_pud))
continue;
if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
vma, addr, next))
return -ENOMEM;
} while (dst_pud++, src_pud++, addr = next, addr != end);
return 0;
}
int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
struct vm_area_struct *vma)
{
pgd_t *src_pgd, *dst_pgd;
unsigned long next;
unsigned long addr = vma->vm_start;
unsigned long end = vma->vm_end;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
bool is_cow;
int ret;
/*
* Don't copy ptes where a page fault will fill them correctly.
* Fork becomes much lighter when there are big shared or private
* readonly mappings. The tradeoff is that copy_page_range is more
* efficient than faulting.
*/
if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
!vma->anon_vma)
return 0;
if (is_vm_hugetlb_page(vma))
return copy_hugetlb_page_range(dst_mm, src_mm, vma);
if (unlikely(vma->vm_flags & VM_PFNMAP)) {
/*
* We do not free on error cases below as remove_vma
* gets called on error from higher level routine
*/
ret = track_pfn_copy(vma);
if (ret)
return ret;
}
/*
* We need to invalidate the secondary MMU mappings only when
* there could be a permission downgrade on the ptes of the
* parent mm. And a permission downgrade will only happen if
* is_cow_mapping() returns true.
*/
is_cow = is_cow_mapping(vma->vm_flags);
mmun_start = addr;
mmun_end = end;
if (is_cow)
mmu_notifier_invalidate_range_start(src_mm, mmun_start,
mmun_end);
ret = 0;
dst_pgd = pgd_offset(dst_mm, addr);
src_pgd = pgd_offset(src_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(src_pgd))
continue;
if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
vma, addr, next))) {
ret = -ENOMEM;
break;
}
} while (dst_pgd++, src_pgd++, addr = next, addr != end);
if (is_cow)
mmu_notifier_invalidate_range_end(src_mm, mmun_start, mmun_end);
return ret;
}
static unsigned long zap_pte_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
struct mm_struct *mm = tlb->mm;
int force_flush = 0;
int rss[NR_MM_COUNTERS];
spinlock_t *ptl;
pte_t *start_pte;
pte_t *pte;
swp_entry_t entry;
again:
init_rss_vec(rss);
start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
pte = start_pte;
arch_enter_lazy_mmu_mode();
do {
pte_t ptent = *pte;
if (pte_none(ptent)) {
continue;
}
if (pte_present(ptent)) {
struct page *page;
page = vm_normal_page(vma, addr, ptent);
if (unlikely(details) && page) {
/*
* unmap_shared_mapping_pages() wants to
* invalidate cache without truncating:
* unmap shared but keep private pages.
*/
if (details->check_mapping &&
details->check_mapping != page->mapping)
continue;
}
ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
tlb_remove_tlb_entry(tlb, pte, addr);
if (unlikely(!page))
continue;
if (PageAnon(page))
rss[MM_ANONPAGES]--;
else {
if (pte_dirty(ptent)) {
force_flush = 1;
set_page_dirty(page);
}
if (pte_young(ptent) &&
likely(!(vma->vm_flags & VM_SEQ_READ)))
mark_page_accessed(page);
rss[MM_FILEPAGES]--;
}
page_remove_rmap(page);
if (unlikely(page_mapcount(page) < 0))
print_bad_pte(vma, addr, ptent, page);
if (unlikely(!__tlb_remove_page(tlb, page))) {
force_flush = 1;
addr += PAGE_SIZE;
break;
}
continue;
}
/* If details->check_mapping, we leave swap entries. */
if (unlikely(details))
continue;
entry = pte_to_swp_entry(ptent);
if (!non_swap_entry(entry))
rss[MM_SWAPENTS]--;
else if (is_migration_entry(entry)) {
struct page *page;
page = migration_entry_to_page(entry);
if (PageAnon(page))
rss[MM_ANONPAGES]--;
else
rss[MM_FILEPAGES]--;
}
if (unlikely(!free_swap_and_cache(entry)))
print_bad_pte(vma, addr, ptent, NULL);
pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
} while (pte++, addr += PAGE_SIZE, addr != end);
add_mm_rss_vec(mm, rss);
arch_leave_lazy_mmu_mode();
/* Do the actual TLB flush before dropping ptl */
if (force_flush)
tlb_flush_mmu_tlbonly(tlb);
pte_unmap_unlock(start_pte, ptl);
/*
* If we forced a TLB flush (either due to running out of
* batch buffers or because we needed to flush dirty TLB
* entries before releasing the ptl), free the batched
* memory too. Restart if we didn't do everything.
*/
if (force_flush) {
force_flush = 0;
tlb_flush_mmu_free(tlb);
if (addr != end)
goto again;
}
return addr;
}
static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) {
#ifdef CONFIG_DEBUG_VM
if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
__func__, addr, end,
vma->vm_start,
vma->vm_end);
BUG();
}
#endif
split_huge_page_pmd(vma, addr, pmd);
} else if (zap_huge_pmd(tlb, vma, pmd, addr))
goto next;
/* fall through */
}
/*
* Here there can be other concurrent MADV_DONTNEED or
* trans huge page faults running, and if the pmd is
* none or trans huge it can change under us. This is
* because MADV_DONTNEED holds the mmap_sem in read
* mode.
*/
if (pmd_none_or_trans_huge_or_clear_bad(pmd))
goto next;
next = zap_pte_range(tlb, vma, pmd, addr, next, details);
next:
cond_resched();
} while (pmd++, addr = next, addr != end);
return addr;
}
static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
next = zap_pmd_range(tlb, vma, pud, addr, next, details);
} while (pud++, addr = next, addr != end);
return addr;
}
static void unmap_page_range(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
struct zap_details *details)
{
pgd_t *pgd;
unsigned long next;
if (details && !details->check_mapping)
details = NULL;
BUG_ON(addr >= end);
tlb_start_vma(tlb, vma);
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
next = zap_pud_range(tlb, vma, pgd, addr, next, details);
} while (pgd++, addr = next, addr != end);
tlb_end_vma(tlb, vma);
}
static void unmap_single_vma(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr,
struct zap_details *details)
{
unsigned long start = max(vma->vm_start, start_addr);
unsigned long end;
if (start >= vma->vm_end)
return;
end = min(vma->vm_end, end_addr);
if (end <= vma->vm_start)
return;
if (vma->vm_file)
uprobe_munmap(vma, start, end);
if (unlikely(vma->vm_flags & VM_PFNMAP))
untrack_pfn(vma, 0, 0);
if (start != end) {
if (unlikely(is_vm_hugetlb_page(vma))) {
/*
* It is undesirable to test vma->vm_file as it
* should be non-null for valid hugetlb area.
* However, vm_file will be NULL in the error
* cleanup path of mmap_region. When
* hugetlbfs ->mmap method fails,
* mmap_region() nullifies vma->vm_file
* before calling this function to clean up.
* Since no pte has actually been setup, it is
* safe to do nothing in this case.
*/
if (vma->vm_file) {
i_mmap_lock_write(vma->vm_file->f_mapping);
__unmap_hugepage_range_final(tlb, vma, start, end, NULL);
i_mmap_unlock_write(vma->vm_file->f_mapping);
}
} else
unmap_page_range(tlb, vma, start, end, details);
}
}
/**
* unmap_vmas - unmap a range of memory covered by a list of vma's
* @tlb: address of the caller's struct mmu_gather
* @vma: the starting vma
* @start_addr: virtual address at which to start unmapping
* @end_addr: virtual address at which to end unmapping
*
* Unmap all pages in the vma list.
*
* Only addresses between `start' and `end' will be unmapped.
*
* The VMA list must be sorted in ascending virtual address order.
*
* unmap_vmas() assumes that the caller will flush the whole unmapped address
* range after unmap_vmas() returns. So the only responsibility here is to
* ensure that any thus-far unmapped pages are flushed before unmap_vmas()
* drops the lock and schedules.
*/
void unmap_vmas(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start_addr,
unsigned long end_addr)
{
struct mm_struct *mm = vma->vm_mm;
mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
}
/**
* zap_page_range - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
* @start: starting address of pages to zap
* @size: number of bytes to zap
* @details: details of shared cache invalidation
*
* Caller must protect the VMA list
*/
void zap_page_range(struct vm_area_struct *vma, unsigned long start,
unsigned long size, struct zap_details *details)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
unsigned long end = start + size;
lru_add_drain();
tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, start, end);
for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
unmap_single_vma(&tlb, vma, start, end, details);
mmu_notifier_invalidate_range_end(mm, start, end);
tlb_finish_mmu(&tlb, start, end);
}
/**
* zap_page_range_single - remove user pages in a given range
* @vma: vm_area_struct holding the applicable pages
* @address: starting address of pages to zap
* @size: number of bytes to zap
* @details: details of shared cache invalidation
*
* The range must fit into one VMA.
*/
static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
unsigned long size, struct zap_details *details)
{
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
unsigned long end = address + size;
lru_add_drain();
tlb_gather_mmu(&tlb, mm, address, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, address, end);
unmap_single_vma(&tlb, vma, address, end, details);
mmu_notifier_invalidate_range_end(mm, address, end);
tlb_finish_mmu(&tlb, address, end);
}
/**
* zap_vma_ptes - remove ptes mapping the vma
* @vma: vm_area_struct holding ptes to be zapped
* @address: starting address of pages to zap
* @size: number of bytes to zap
*
* This function only unmaps ptes assigned to VM_PFNMAP vmas.
*
* The entire address range must be fully contained within the vma.
*
* Returns 0 if successful.
*/
int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
unsigned long size)
{
if (address < vma->vm_start || address + size > vma->vm_end ||
!(vma->vm_flags & VM_PFNMAP))
return -1;
zap_page_range_single(vma, address, size, NULL);
return 0;
}
EXPORT_SYMBOL_GPL(zap_vma_ptes);
pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
{
pgd_t * pgd = pgd_offset(mm, addr);
pud_t * pud = pud_alloc(mm, pgd, addr);
if (pud) {
pmd_t * pmd = pmd_alloc(mm, pud, addr);
if (pmd) {
VM_BUG_ON(pmd_trans_huge(*pmd));
return pte_alloc_map_lock(mm, pmd, addr, ptl);
}
}
return NULL;
}
/*
* This is the old fallback for page remapping.
*
* For historical reasons, it only allows reserved pages. Only
* old drivers should use this, and they needed to mark their
* pages reserved for the old functions anyway.
*/
static int insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page, pgprot_t prot)
{
struct mm_struct *mm = vma->vm_mm;
int retval;
pte_t *pte;
spinlock_t *ptl;
retval = -EINVAL;
if (PageAnon(page))
goto out;
retval = -ENOMEM;
flush_dcache_page(page);
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
goto out;
retval = -EBUSY;
if (!pte_none(*pte))
goto out_unlock;
/* Ok, finally just insert the thing.. */
get_page(page);
inc_mm_counter_fast(mm, MM_FILEPAGES);
page_add_file_rmap(page);
set_pte_at(mm, addr, pte, mk_pte(page, prot));
retval = 0;
pte_unmap_unlock(pte, ptl);
return retval;
out_unlock:
pte_unmap_unlock(pte, ptl);
out:
return retval;
}
/**
* vm_insert_page - insert single page into user vma
* @vma: user vma to map to
* @addr: target user address of this page
* @page: source kernel page
*
* This allows drivers to insert individual pages they've allocated
* into a user vma.
*
* The page has to be a nice clean _individual_ kernel allocation.
* If you allocate a compound page, you need to have marked it as
* such (__GFP_COMP), or manually just split the page up yourself
* (see split_page()).
*
* NOTE! Traditionally this was done with "remap_pfn_range()" which
* took an arbitrary page protection parameter. This doesn't allow
* that. Your vma protection will have to be set up correctly, which
* means that if you want a shared writable mapping, you'd better
* ask for a shared writable mapping!
*
* The page does not need to be reserved.
*
* Usually this function is called from f_op->mmap() handler
* under mm->mmap_sem write-lock, so it can change vma->vm_flags.
* Caller must set VM_MIXEDMAP on vma if it wants to call this
* function from other places, for example from page-fault handler.
*/
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page)
{
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
if (!page_count(page))
return -EINVAL;
if (!(vma->vm_flags & VM_MIXEDMAP)) {
BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
BUG_ON(vma->vm_flags & VM_PFNMAP);
vma->vm_flags |= VM_MIXEDMAP;
}
return insert_page(vma, addr, page, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_page);
static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, pgprot_t prot)
{
struct mm_struct *mm = vma->vm_mm;
int retval;
pte_t *pte, entry;
spinlock_t *ptl;
retval = -ENOMEM;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
goto out;
retval = -EBUSY;
if (!pte_none(*pte))
goto out_unlock;
/* Ok, finally just insert the thing.. */
entry = pte_mkspecial(pfn_pte(pfn, prot));
set_pte_at(mm, addr, pte, entry);
update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
retval = 0;
out_unlock:
pte_unmap_unlock(pte, ptl);
out:
return retval;
}
/**
* vm_insert_pfn - insert single pfn into user vma
* @vma: user vma to map to
* @addr: target user address of this page
* @pfn: source kernel pfn
*
* Similar to vm_insert_page, this allows drivers to insert individual pages
* they've allocated into a user vma. Same comments apply.
*
* This function should only be called from a vm_ops->fault handler, and
* in that case the handler should return NULL.
*
* vma cannot be a COW mapping.
*
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
*/
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
int ret;
pgprot_t pgprot = vma->vm_page_prot;
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
* consistency in testing and feature parity among all, so we should
* try to keep these invariants in place for everybody.
*/
BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
(VM_PFNMAP|VM_MIXEDMAP));
BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
if (track_pfn_insert(vma, &pgprot, pfn))
return -EINVAL;
ret = insert_pfn(vma, addr, pfn, pgprot);
return ret;
}
EXPORT_SYMBOL(vm_insert_pfn);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
/*
* If we don't have pte special, then we have to use the pfn_valid()
* based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
* refcount the page if pfn_valid is true (hence insert_page rather
* than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP
* without pte special, it would there be refcounted as a normal page.
*/
if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
struct page *page;
page = pfn_to_page(pfn);
return insert_page(vma, addr, page, vma->vm_page_prot);
}
return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_mixed);
/*
* maps a range of physical memory into the requested pages. the old
* mappings are removed. any references to nonexistent pages results
* in null mappings (currently treated as "copy-on-access")
*/
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pte_t *pte;
spinlock_t *ptl;
pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
arch_enter_lazy_mmu_mode();
do {
BUG_ON(!pte_none(*pte));
set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
return 0;
}
static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pmd_t *pmd;
unsigned long next;
pfn -= addr >> PAGE_SHIFT;
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return -ENOMEM;
VM_BUG_ON(pmd_trans_huge(*pmd));
do {
next = pmd_addr_end(addr, end);
if (remap_pte_range(mm, pmd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pud_t *pud;
unsigned long next;
pfn -= addr >> PAGE_SHIFT;
pud = pud_alloc(mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (remap_pmd_range(mm, pud, addr, next,
pfn + (addr >> PAGE_SHIFT), prot))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
/**
* remap_pfn_range - remap kernel memory to userspace
* @vma: user vma to map to
* @addr: target user address to start at
* @pfn: physical address of kernel memory
* @size: size of map area
* @prot: page protection flags for this mapping
*
* Note: this is only safe if the mm semaphore is held when called.
*/
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
{
pgd_t *pgd;
unsigned long next;
unsigned long end = addr + PAGE_ALIGN(size);
struct mm_struct *mm = vma->vm_mm;
int err;
/*
* Physically remapped pages are special. Tell the
* rest of the world about it:
* VM_IO tells people not to look at these pages
* (accesses can have side effects).
* VM_PFNMAP tells the core MM that the base pages are just
* raw PFN mappings, and do not have a "struct page" associated
* with them.
* VM_DONTEXPAND
* Disable vma merging and expanding with mremap().
* VM_DONTDUMP
* Omit vma from core dump, even when VM_IO turned off.
*
* There's a horrible special case to handle copy-on-write
* behaviour that some programs depend on. We mark the "original"
* un-COW'ed pages by matching them up with "vma->vm_pgoff".
* See vm_normal_page() for details.
*/
if (is_cow_mapping(vma->vm_flags)) {
if (addr != vma->vm_start || end != vma->vm_end)
return -EINVAL;
vma->vm_pgoff = pfn;
}
err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
if (err)
return -EINVAL;
vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
do {
next = pgd_addr_end(addr, end);
err = remap_pud_range(mm, pgd, addr, next,
pfn + (addr >> PAGE_SHIFT), prot);
if (err)
break;
} while (pgd++, addr = next, addr != end);
if (err)
untrack_pfn(vma, pfn, PAGE_ALIGN(size));
return err;
}
EXPORT_SYMBOL(remap_pfn_range);
/**
* vm_iomap_memory - remap memory to userspace
* @vma: user vma to map to
* @start: start of area
* @len: size of area
*
* This is a simplified io_remap_pfn_range() for common driver use. The
* driver just needs to give us the physical memory range to be mapped,
* we'll figure out the rest from the vma information.
*
* NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
* whatever write-combining details or similar.
*/
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
{
unsigned long vm_len, pfn, pages;
/* Check that the physical memory area passed in looks valid */
if (start + len < start)
return -EINVAL;
/*
* You *really* shouldn't map things that aren't page-aligned,
* but we've historically allowed it because IO memory might
* just have smaller alignment.
*/
len += start & ~PAGE_MASK;
pfn = start >> PAGE_SHIFT;
pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
if (pfn + pages < pfn)
return -EINVAL;
/* We start the mapping 'vm_pgoff' pages into the area */
if (vma->vm_pgoff > pages)
return -EINVAL;
pfn += vma->vm_pgoff;
pages -= vma->vm_pgoff;
/* Can we fit all of the mapping? */
vm_len = vma->vm_end - vma->vm_start;
if (vm_len >> PAGE_SHIFT > pages)
return -EINVAL;
/* Ok, let it rip */
return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_iomap_memory);
static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data)
{
pte_t *pte;
int err;
pgtable_t token;
spinlock_t *uninitialized_var(ptl);
pte = (mm == &init_mm) ?
pte_alloc_kernel(pmd, addr) :
pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
BUG_ON(pmd_huge(*pmd));
arch_enter_lazy_mmu_mode();
token = pmd_pgtable(*pmd);
do {
err = fn(pte++, token, addr, data);
if (err)
break;
} while (addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
if (mm != &init_mm)
pte_unmap_unlock(pte-1, ptl);
return err;
}
static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data)
{
pmd_t *pmd;
unsigned long next;
int err;
BUG_ON(pud_huge(*pud));
pmd = pmd_alloc(mm, pud, addr);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
if (err)
break;
} while (pmd++, addr = next, addr != end);
return err;
}
static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data)
{
pud_t *pud;
unsigned long next;
int err;
pud = pud_alloc(mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
if (err)
break;
} while (pud++, addr = next, addr != end);
return err;
}
/*
* Scan a region of virtual memory, filling in page tables as necessary
* and calling a provided function on each leaf page table.
*/
int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
unsigned long size, pte_fn_t fn, void *data)
{
pgd_t *pgd;
unsigned long next;
unsigned long end = addr + size;
int err;
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
if (err)
break;
} while (pgd++, addr = next, addr != end);
return err;
}
EXPORT_SYMBOL_GPL(apply_to_page_range);
/*
* handle_pte_fault chooses page fault handler according to an entry which was
* read non-atomically. Before making any commitment, on those architectures
* or configurations (e.g. i386 with PAE) which might give a mix of unmatched
* parts, do_swap_page must check under lock before unmapping the pte and
* proceeding (but do_wp_page is only called after already making such a check;
* and do_anonymous_page can safely check later on).
*/
static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
pte_t *page_table, pte_t orig_pte)
{
int same = 1;
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
if (sizeof(pte_t) > sizeof(unsigned long)) {
spinlock_t *ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
same = pte_same(*page_table, orig_pte);
spin_unlock(ptl);
}
#endif
pte_unmap(page_table);
return same;
}
static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
{
debug_dma_assert_idle(src);
/*
* If the source page was a PFN mapping, we don't have
* a "struct page" for it. We do a best-effort copy by
* just copying from the original user address. If that
* fails, we just zero-fill it. Live with it.
*/
if (unlikely(!src)) {
void *kaddr = kmap_atomic(dst);
void __user *uaddr = (void __user *)(va & PAGE_MASK);
/*
* This really shouldn't fail, because the page is there
* in the page tables. But it might just be unreadable,
* in which case we just give up and fill the result with
* zeroes.
*/
if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
clear_page(kaddr);
kunmap_atomic(kaddr);
flush_dcache_page(dst);
} else
copy_user_highpage(dst, src, va, vma);
}
/*
* Notify the address space that the page is about to become writable so that
* it can prohibit this or wait for the page to get into an appropriate state.
*
* We do this without the lock held, so that it can sleep if it needs to.
*/
static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
unsigned long address)
{
struct vm_fault vmf;
int ret;
vmf.virtual_address = (void __user *)(address & PAGE_MASK);
vmf.pgoff = page->index;
vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
vmf.page = page;
vmf.cow_page = NULL;
ret = vma->vm_ops->page_mkwrite(vma, &vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
return ret;
if (unlikely(!(ret & VM_FAULT_LOCKED))) {
lock_page(page);
if (!page->mapping) {
unlock_page(page);
return 0; /* retry */
}
ret |= VM_FAULT_LOCKED;
} else
VM_BUG_ON_PAGE(!PageLocked(page), page);
return ret;
}
/*
* Handle write page faults for pages that can be reused in the current vma
*
* This can happen either due to the mapping being with the VM_SHARED flag,
* or due to us being the last reference standing to the page. In either
* case, all we need to do here is to mark the page as writable and update
* any related book-keeping.
*/
static inline int wp_page_reuse(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pte_t *page_table, spinlock_t *ptl, pte_t orig_pte,
struct page *page, int page_mkwrite,
int dirty_shared)
__releases(ptl)
{
pte_t entry;
/*
* Clear the pages cpupid information as the existing
* information potentially belongs to a now completely
* unrelated process.
*/
if (page)
page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1);
flush_cache_page(vma, address, pte_pfn(orig_pte));
entry = pte_mkyoung(orig_pte);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (ptep_set_access_flags(vma, address, page_table, entry, 1))
update_mmu_cache(vma, address, page_table);
pte_unmap_unlock(page_table, ptl);
if (dirty_shared) {
struct address_space *mapping;
int dirtied;
if (!page_mkwrite)
lock_page(page);
dirtied = set_page_dirty(page);
VM_BUG_ON_PAGE(PageAnon(page), page);
mapping = page->mapping;
unlock_page(page);
page_cache_release(page);
if ((dirtied || page_mkwrite) && mapping) {
/*
* Some device drivers do not set page.mapping
* but still dirty their pages
*/
balance_dirty_pages_ratelimited(mapping);
}
if (!page_mkwrite)
file_update_time(vma->vm_file);
}
return VM_FAULT_WRITE;
}
/*
* Handle the case of a page which we actually need to copy to a new page.
*
* Called with mmap_sem locked and the old page referenced, but
* without the ptl held.
*
* High level logic flow:
*
* - Allocate a page, copy the content of the old page to the new one.
* - Handle book keeping and accounting - cgroups, mmu-notifiers, etc.
* - Take the PTL. If the pte changed, bail out and release the allocated page
* - If the pte is still the way we remember it, update the page table and all
* relevant references. This includes dropping the reference the page-table
* held to the old page, as well as updating the rmap.
* - In any case, unlock the PTL and drop the reference we took to the old page.
*/
static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
pte_t orig_pte, struct page *old_page)
{
struct page *new_page = NULL;
spinlock_t *ptl = NULL;
pte_t entry;
int page_copied = 0;
const unsigned long mmun_start = address & PAGE_MASK; /* For mmu_notifiers */
const unsigned long mmun_end = mmun_start + PAGE_SIZE; /* For mmu_notifiers */
struct mem_cgroup *memcg;
if (unlikely(anon_vma_prepare(vma)))
goto oom;
if (is_zero_pfn(pte_pfn(orig_pte))) {
new_page = alloc_zeroed_user_highpage_movable(vma, address);
if (!new_page)
goto oom;
} else {
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
if (!new_page)
goto oom;
cow_user_page(new_page, old_page, address, vma);
}
if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg))
goto oom_free_new;
__SetPageUptodate(new_page);
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
/*
* Re-check the pte - we dropped the lock
*/
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (likely(pte_same(*page_table, orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
dec_mm_counter_fast(mm, MM_FILEPAGES);
inc_mm_counter_fast(mm, MM_ANONPAGES);
}
} else {
inc_mm_counter_fast(mm, MM_ANONPAGES);
}
flush_cache_page(vma, address, pte_pfn(orig_pte));
entry = mk_pte(new_page, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
/*
* Clear the pte entry and flush it first, before updating the
* pte with the new entry. This will avoid a race condition
* seen in the presence of one thread doing SMC and another
* thread doing COW.
*/
ptep_clear_flush_notify(vma, address, page_table);
page_add_new_anon_rmap(new_page, vma, address);
mem_cgroup_commit_charge(new_page, memcg, false);
lru_cache_add_active_or_unevictable(new_page, vma);
/*
* We call the notify macro here because, when using secondary
* mmu page tables (such as kvm shadow page tables), we want the
* new page to be mapped directly into the secondary page table.
*/
set_pte_at_notify(mm, address, page_table, entry);
update_mmu_cache(vma, address, page_table);
if (old_page) {
/*
* Only after switching the pte to the new page may
* we remove the mapcount here. Otherwise another
* process may come and find the rmap count decremented
* before the pte is switched to the new page, and
* "reuse" the old page writing into it while our pte
* here still points into it and can be read by other
* threads.
*
* The critical issue is to order this
* page_remove_rmap with the ptp_clear_flush above.
* Those stores are ordered by (if nothing else,)
* the barrier present in the atomic_add_negative
* in page_remove_rmap.
*
* Then the TLB flush in ptep_clear_flush ensures that
* no process can access the old page before the
* decremented mapcount is visible. And the old page
* cannot be reused until after the decremented
* mapcount is visible. So transitively, TLBs to
* old page will be flushed before it can be reused.
*/
page_remove_rmap(old_page);
}
/* Free the old page.. */
new_page = old_page;
page_copied = 1;
} else {
mem_cgroup_cancel_charge(new_page, memcg);
}
if (new_page)
page_cache_release(new_page);
pte_unmap_unlock(page_table, ptl);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
if (old_page) {
/*
* Don't let another task, with possibly unlocked vma,
* keep the mlocked page.
*/
if (page_copied && (vma->vm_flags & VM_LOCKED)) {
lock_page(old_page); /* LRU manipulation */
munlock_vma_page(old_page);
unlock_page(old_page);
}
page_cache_release(old_page);
}
return page_copied ? VM_FAULT_WRITE : 0;
oom_free_new:
page_cache_release(new_page);
oom:
if (old_page)
page_cache_release(old_page);
return VM_FAULT_OOM;
}
/*
* Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED
* mapping
*/
static int wp_pfn_shared(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pte_t *page_table, spinlock_t *ptl, pte_t orig_pte,
pmd_t *pmd)
{
if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) {
struct vm_fault vmf = {
.page = NULL,
.pgoff = linear_page_index(vma, address),
.virtual_address = (void __user *)(address & PAGE_MASK),
.flags = FAULT_FLAG_WRITE | FAULT_FLAG_MKWRITE,
};
int ret;
pte_unmap_unlock(page_table, ptl);
ret = vma->vm_ops->pfn_mkwrite(vma, &vmf);
if (ret & VM_FAULT_ERROR)
return ret;
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
/*
* We might have raced with another page fault while we
* released the pte_offset_map_lock.
*/
if (!pte_same(*page_table, orig_pte)) {
pte_unmap_unlock(page_table, ptl);
return 0;
}
}
return wp_page_reuse(mm, vma, address, page_table, ptl, orig_pte,
NULL, 0, 0);
}
static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table,
pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte,
struct page *old_page)
__releases(ptl)
{
int page_mkwrite = 0;
page_cache_get(old_page);
/*
* Only catch write-faults on shared writable pages,
* read-only shared pages can get COWed by
* get_user_pages(.write=1, .force=1).
*/
if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
int tmp;
pte_unmap_unlock(page_table, ptl);
tmp = do_page_mkwrite(vma, old_page, address);
if (unlikely(!tmp || (tmp &
(VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
page_cache_release(old_page);
return tmp;
}
/*
* Since we dropped the lock we need to revalidate
* the PTE as someone else may have changed it. If
* they did, we just return, as we can count on the
* MMU to tell us if they didn't also make it writable.
*/
page_table = pte_offset_map_lock(mm, pmd, address,
&ptl);
if (!pte_same(*page_table, orig_pte)) {
unlock_page(old_page);
pte_unmap_unlock(page_table, ptl);
page_cache_release(old_page);
return 0;
}
page_mkwrite = 1;
}
return wp_page_reuse(mm, vma, address, page_table, ptl,
orig_pte, old_page, page_mkwrite, 1);
}
/*
* This routine handles present pages, when users try to write
* to a shared page. It is done by copying the page to a new address
* and decrementing the shared-page counter for the old page.
*
* Note that this routine assumes that the protection checks have been
* done by the caller (the low-level page fault routine in most cases).
* Thus we can safely just mark it writable once we've done any necessary
* COW.
*
* We also mark the page dirty at this point even though the page will
* change only once the write actually happens. This avoids a few races,
* and potentially makes it more efficient.
*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), with pte both mapped and locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
*/
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
spinlock_t *ptl, pte_t orig_pte)
__releases(ptl)
{
struct page *old_page;
old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page) {
/*
* VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
* VM_PFNMAP VMA.
*
* We should not cow pages in a shared writeable mapping.
* Just mark the pages writable and/or call ops->pfn_mkwrite.
*/
if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))
return wp_pfn_shared(mm, vma, address, page_table, ptl,
orig_pte, pmd);
pte_unmap_unlock(page_table, ptl);
return wp_page_copy(mm, vma, address, page_table, pmd,
orig_pte, old_page);
}
/*
* Take out anonymous pages first, anonymous shared vmas are
* not dirty accountable.
*/
if (PageAnon(old_page) && !PageKsm(old_page)) {
if (!trylock_page(old_page)) {
page_cache_get(old_page);
pte_unmap_unlock(page_table, ptl);
lock_page(old_page);
page_table = pte_offset_map_lock(mm, pmd, address,
&ptl);
if (!pte_same(*page_table, orig_pte)) {
unlock_page(old_page);
pte_unmap_unlock(page_table, ptl);
page_cache_release(old_page);
return 0;
}
page_cache_release(old_page);
}
if (reuse_swap_page(old_page)) {
/*
* The page is all ours. Move it to our anon_vma so
* the rmap code will not search our parent or siblings.
* Protected against the rmap code by the page lock.
*/
page_move_anon_rmap(old_page, vma, address);
unlock_page(old_page);
return wp_page_reuse(mm, vma, address, page_table, ptl,
orig_pte, old_page, 0, 0);
}
unlock_page(old_page);
} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))) {
return wp_page_shared(mm, vma, address, page_table, pmd,
ptl, orig_pte, old_page);
}
/*
* Ok, we need to copy. Oh, well..
*/
page_cache_get(old_page);
pte_unmap_unlock(page_table, ptl);
return wp_page_copy(mm, vma, address, page_table, pmd,
orig_pte, old_page);
}
static void unmap_mapping_range_vma(struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr,
struct zap_details *details)
{
zap_page_range_single(vma, start_addr, end_addr - start_addr, details);
}
static inline void unmap_mapping_range_tree(struct rb_root *root,
struct zap_details *details)
{
struct vm_area_struct *vma;
pgoff_t vba, vea, zba, zea;
vma_interval_tree_foreach(vma, root,
details->first_index, details->last_index) {
vba = vma->vm_pgoff;
vea = vba + vma_pages(vma) - 1;
/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
zba = details->first_index;
if (zba < vba)
zba = vba;
zea = details->last_index;
if (zea > vea)
zea = vea;
unmap_mapping_range_vma(vma,
((zba - vba) << PAGE_SHIFT) + vma->vm_start,
((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
details);
}
}
/**
* unmap_mapping_range - unmap the portion of all mmaps in the specified
* address_space corresponding to the specified page range in the underlying
* file.
*
* @mapping: the address space containing mmaps to be unmapped.
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
* boundary. Note that this is different from truncate_pagecache(), which
* must keep the partial page. In contrast, we must get rid of
* partial pages.
* @holelen: size of prospective hole in bytes. This will be rounded
* up to a PAGE_SIZE boundary. A holelen of zero truncates to the
* end of the file.
* @even_cows: 1 when truncating a file, unmap even private COWed pages;
* but 0 when invalidating pagecache, don't throw away private data.
*/
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows)
{
struct zap_details details;
pgoff_t hba = holebegin >> PAGE_SHIFT;
pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
/* Check for overflow. */
if (sizeof(holelen) > sizeof(hlen)) {
long long holeend =
(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (holeend & ~(long long)ULONG_MAX)
hlen = ULONG_MAX - hba + 1;
}
details.check_mapping = even_cows? NULL: mapping;
details.first_index = hba;
details.last_index = hba + hlen - 1;
if (details.last_index < details.first_index)
details.last_index = ULONG_MAX;
/* DAX uses i_mmap_lock to serialise file truncate vs page fault */
i_mmap_lock_write(mapping);
if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
i_mmap_unlock_write(mapping);
}
EXPORT_SYMBOL(unmap_mapping_range);
/*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with pte unmapped and unlocked.
*
* We return with the mmap_sem locked or unlocked in the same cases
* as does filemap_fault().
*/
static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
unsigned int flags, pte_t orig_pte)
{
spinlock_t *ptl;
struct page *page, *swapcache;
struct mem_cgroup *memcg;
swp_entry_t entry;
pte_t pte;
int locked;
int exclusive = 0;
int ret = 0;
if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
goto out;
entry = pte_to_swp_entry(orig_pte);
if (unlikely(non_swap_entry(entry))) {
if (is_migration_entry(entry)) {
migration_entry_wait(mm, pmd, address);
} else if (is_hwpoison_entry(entry)) {
ret = VM_FAULT_HWPOISON;
} else {
print_bad_pte(vma, address, orig_pte, NULL);
ret = VM_FAULT_SIGBUS;
}
goto out;
}
delayacct_set_flag(DELAYACCT_PF_SWAPIN);
page = lookup_swap_cache(entry);
if (!page) {
page = swapin_readahead(entry,
GFP_HIGHUSER_MOVABLE, vma, address);
if (!page) {
/*
* Back out if somebody else faulted in this pte
* while we released the pte lock.
*/
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (likely(pte_same(*page_table, orig_pte)))
ret = VM_FAULT_OOM;
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
goto unlock;
}
/* Had to read the page from swap area: Major fault */
ret = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(mm, PGMAJFAULT);
} else if (PageHWPoison(page)) {
/*
* hwpoisoned dirty swapcache pages are kept for killing
* owner processes (which may be unknown at hwpoison time)
*/
ret = VM_FAULT_HWPOISON;
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
swapcache = page;
goto out_release;
}
swapcache = page;
locked = lock_page_or_retry(page, mm, flags);
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
if (!locked) {
ret |= VM_FAULT_RETRY;
goto out_release;
}
/*
* Make sure try_to_free_swap or reuse_swap_page or swapoff did not
* release the swapcache from under us. The page pin, and pte_same
* test below, are not enough to exclude that. Even if it is still
* swapcache, we need to check that the page's swap has not changed.
*/
if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val))
goto out_page;
page = ksm_might_need_to_copy(page, vma, address);
if (unlikely(!page)) {
ret = VM_FAULT_OOM;
page = swapcache;
goto out_page;
}
if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) {
ret = VM_FAULT_OOM;
goto out_page;
}
/*
* Back out if somebody else already faulted in this pte.
*/
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (unlikely(!pte_same(*page_table, orig_pte)))
goto out_nomap;
if (unlikely(!PageUptodate(page))) {
ret = VM_FAULT_SIGBUS;
goto out_nomap;
}
/*
* The page isn't present yet, go ahead with the fault.
*
* Be careful about the sequence of operations here.
* To get its accounting right, reuse_swap_page() must be called
* while the page is counted on swap but not yet in mapcount i.e.
* before page_add_anon_rmap() and swap_free(); try_to_free_swap()
* must be called after the swap_free(), or it will never succeed.
*/
inc_mm_counter_fast(mm, MM_ANONPAGES);
dec_mm_counter_fast(mm, MM_SWAPENTS);
pte = mk_pte(page, vma->vm_page_prot);
if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
flags &= ~FAULT_FLAG_WRITE;
ret |= VM_FAULT_WRITE;
exclusive = 1;
}
flush_icache_page(vma, page);
if (pte_swp_soft_dirty(orig_pte))
pte = pte_mksoft_dirty(pte);
set_pte_at(mm, address, page_table, pte);
if (page == swapcache) {
do_page_add_anon_rmap(page, vma, address, exclusive);
mem_cgroup_commit_charge(page, memcg, true);
} else { /* ksm created a completely new copy */
page_add_new_anon_rmap(page, vma, address);
mem_cgroup_commit_charge(page, memcg, false);
lru_cache_add_active_or_unevictable(page, vma);
}
swap_free(entry);
if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
try_to_free_swap(page);
unlock_page(page);
if (page != swapcache) {
/*
* Hold the lock to avoid the swap entry to be reused
* until we take the PT lock for the pte_same() check
* (to avoid false positives from pte_same). For
* further safety release the lock after the swap_free
* so that the swap count won't change under a
* parallel locked swapcache.
*/
unlock_page(swapcache);
page_cache_release(swapcache);
}
if (flags & FAULT_FLAG_WRITE) {
ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
if (ret & VM_FAULT_ERROR)
ret &= VM_FAULT_ERROR;
goto out;
}
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, page_table);
unlock:
pte_unmap_unlock(page_table, ptl);
out:
return ret;
out_nomap:
mem_cgroup_cancel_charge(page, memcg);
pte_unmap_unlock(page_table, ptl);
out_page:
unlock_page(page);
out_release:
page_cache_release(page);
if (page != swapcache) {
unlock_page(swapcache);
page_cache_release(swapcache);
}
return ret;
}
/*
* This is like a special single-page "expand_{down|up}wards()",
* except we must first make sure that 'address{-|+}PAGE_SIZE'
* doesn't hit another vma.
*/
static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
{
address &= PAGE_MASK;
if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
struct vm_area_struct *prev = vma->vm_prev;
/*
* Is there a mapping abutting this one below?
*
* That's only ok if it's the same stack mapping
* that has gotten split..
*/
if (prev && prev->vm_end == address)
return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
return expand_downwards(vma, address - PAGE_SIZE);
}
if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
struct vm_area_struct *next = vma->vm_next;
/* As VM_GROWSDOWN but s/below/above/ */
if (next && next->vm_start == address + PAGE_SIZE)
return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
return expand_upwards(vma, address + PAGE_SIZE);
}
return 0;
}
/*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
*/
static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
unsigned int flags)
{
struct mem_cgroup *memcg;
struct page *page;
spinlock_t *ptl;
pte_t entry;
pte_unmap(page_table);
/* File mapping without ->vm_ops ? */
if (vma->vm_flags & VM_SHARED)
return VM_FAULT_SIGBUS;
/* Check if we need to add a guard page to the stack */
if (check_stack_guard_page(vma, address) < 0)
return VM_FAULT_SIGSEGV;
/* Use the zero-page for reads */
if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
vma->vm_page_prot));
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!pte_none(*page_table))
goto unlock;
goto setpte;
}
/* Allocate our own private page. */
if (unlikely(anon_vma_prepare(vma)))
goto oom;
page = alloc_zeroed_user_highpage_movable(vma, address);
if (!page)
goto oom;
if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg))
goto oom_free_page;
/*
* The memory barrier inside __SetPageUptodate makes sure that
* preceeding stores to the page contents become visible before
* the set_pte_at() write.
*/
__SetPageUptodate(page);
entry = mk_pte(page, vma->vm_page_prot);
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!pte_none(*page_table))
goto release;
inc_mm_counter_fast(mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
mem_cgroup_commit_charge(page, memcg, false);
lru_cache_add_active_or_unevictable(page, vma);
setpte:
set_pte_at(mm, address, page_table, entry);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, page_table);
unlock:
pte_unmap_unlock(page_table, ptl);
return 0;
release:
mem_cgroup_cancel_charge(page, memcg);
page_cache_release(page);
goto unlock;
oom_free_page:
page_cache_release(page);
oom:
return VM_FAULT_OOM;
}
/*
* The mmap_sem must have been held on entry, and may have been
* released depending on flags and vma->vm_ops->fault() return value.
* See filemap_fault() and __lock_page_retry().
*/
static int __do_fault(struct vm_area_struct *vma, unsigned long address,
pgoff_t pgoff, unsigned int flags,
struct page *cow_page, struct page **page)
{
struct vm_fault vmf;
int ret;
vmf.virtual_address = (void __user *)(address & PAGE_MASK);
vmf.pgoff = pgoff;
vmf.flags = flags;
vmf.page = NULL;
vmf.cow_page = cow_page;
ret = vma->vm_ops->fault(vma, &vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
if (!vmf.page)
goto out;
if (unlikely(PageHWPoison(vmf.page))) {
if (ret & VM_FAULT_LOCKED)
unlock_page(vmf.page);
page_cache_release(vmf.page);
return VM_FAULT_HWPOISON;
}
if (unlikely(!(ret & VM_FAULT_LOCKED)))
lock_page(vmf.page);
else
VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);
out:
*page = vmf.page;
return ret;
}
/**
* do_set_pte - setup new PTE entry for given page and add reverse page mapping.
*
* @vma: virtual memory area
* @address: user virtual address
* @page: page to map
* @pte: pointer to target page table entry
* @write: true, if new entry is writable
* @anon: true, if it's anonymous page
*
* Caller must hold page table lock relevant for @pte.
*
* Target users are page handler itself and implementations of
* vm_ops->map_pages.
*/
void do_set_pte(struct vm_area_struct *vma, unsigned long address,
struct page *page, pte_t *pte, bool write, bool anon)
{
pte_t entry;
flush_icache_page(vma, page);
entry = mk_pte(page, vma->vm_page_prot);
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (anon) {
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
} else {
inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
page_add_file_rmap(page);
}
set_pte_at(vma->vm_mm, address, pte, entry);
/* no need to invalidate: a not-present page won't be cached */
update_mmu_cache(vma, address, pte);
}
static unsigned long fault_around_bytes __read_mostly =
rounddown_pow_of_two(65536);
#ifdef CONFIG_DEBUG_FS
static int fault_around_bytes_get(void *data, u64 *val)
{
*val = fault_around_bytes;
return 0;
}
/*
* fault_around_pages() and fault_around_mask() expects fault_around_bytes
* rounded down to nearest page order. It's what do_fault_around() expects to
* see.
*/
static int fault_around_bytes_set(void *data, u64 val)
{
if (val / PAGE_SIZE > PTRS_PER_PTE)
return -EINVAL;
if (val > PAGE_SIZE)
fault_around_bytes = rounddown_pow_of_two(val);
else
fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops,
fault_around_bytes_get, fault_around_bytes_set, "%llu\n");
static int __init fault_around_debugfs(void)
{
void *ret;
ret = debugfs_create_file("fault_around_bytes", 0644, NULL, NULL,
&fault_around_bytes_fops);
if (!ret)
pr_warn("Failed to create fault_around_bytes in debugfs");
return 0;
}
late_initcall(fault_around_debugfs);
#endif
/*
* do_fault_around() tries to map few pages around the fault address. The hope
* is that the pages will be needed soon and this will lower the number of
* faults to handle.
*
* It uses vm_ops->map_pages() to map the pages, which skips the page if it's
* not ready to be mapped: not up-to-date, locked, etc.
*
* This function is called with the page table lock taken. In the split ptlock
* case the page table lock only protects only those entries which belong to
* the page table corresponding to the fault address.
*
* This function doesn't cross the VMA boundaries, in order to call map_pages()
* only once.
*
* fault_around_pages() defines how many pages we'll try to map.
* do_fault_around() expects it to return a power of two less than or equal to
* PTRS_PER_PTE.
*
* The virtual address of the area that we map is naturally aligned to the
* fault_around_pages() value (and therefore to page order). This way it's
* easier to guarantee that we don't cross page table boundaries.
*/
static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
pte_t *pte, pgoff_t pgoff, unsigned int flags)
{
unsigned long start_addr, nr_pages, mask;
pgoff_t max_pgoff;
struct vm_fault vmf;
int off;
nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT;
mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK;
start_addr = max(address & mask, vma->vm_start);
off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
pte -= off;
pgoff -= off;
/*
* max_pgoff is either end of page table or end of vma
* or fault_around_pages() from pgoff, depending what is nearest.
*/
max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
PTRS_PER_PTE - 1;
max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1,
pgoff + nr_pages - 1);
/* Check if it makes any sense to call ->map_pages */
while (!pte_none(*pte)) {
if (++pgoff > max_pgoff)
return;
start_addr += PAGE_SIZE;
if (start_addr >= vma->vm_end)
return;
pte++;
}
vmf.virtual_address = (void __user *) start_addr;
vmf.pte = pte;
vmf.pgoff = pgoff;
vmf.max_pgoff = max_pgoff;
vmf.flags = flags;
vma->vm_ops->map_pages(vma, &vmf);
}
static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
struct page *fault_page;
spinlock_t *ptl;
pte_t *pte;
int ret = 0;
/*
* Let's call ->map_pages() first and use ->fault() as fallback
* if page by the offset is not ready to be mapped (cold cache or
* something).
*/
if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
do_fault_around(vma, address, pte, pgoff, flags);
if (!pte_same(*pte, orig_pte))
goto unlock_out;
pte_unmap_unlock(pte, ptl);
}
ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
if (unlikely(!pte_same(*pte, orig_pte))) {
pte_unmap_unlock(pte, ptl);
unlock_page(fault_page);
page_cache_release(fault_page);
return ret;
}
do_set_pte(vma, address, fault_page, pte, false, false);
unlock_page(fault_page);
unlock_out:
pte_unmap_unlock(pte, ptl);
return ret;
}
static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
struct page *fault_page, *new_page;
struct mem_cgroup *memcg;
spinlock_t *ptl;
pte_t *pte;
int ret;
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
if (!new_page)
return VM_FAULT_OOM;
if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) {
page_cache_release(new_page);
return VM_FAULT_OOM;
}
ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
goto uncharge_out;
if (fault_page)
copy_user_highpage(new_page, fault_page, address, vma);
__SetPageUptodate(new_page);
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
if (unlikely(!pte_same(*pte, orig_pte))) {
pte_unmap_unlock(pte, ptl);
if (fault_page) {
unlock_page(fault_page);
page_cache_release(fault_page);
} else {
/*
* The fault handler has no page to lock, so it holds
* i_mmap_lock for read to protect against truncate.
*/
i_mmap_unlock_read(vma->vm_file->f_mapping);
}
goto uncharge_out;
}
do_set_pte(vma, address, new_page, pte, true, true);
mem_cgroup_commit_charge(new_page, memcg, false);
lru_cache_add_active_or_unevictable(new_page, vma);
pte_unmap_unlock(pte, ptl);
if (fault_page) {
unlock_page(fault_page);
page_cache_release(fault_page);
} else {
/*
* The fault handler has no page to lock, so it holds
* i_mmap_lock for read to protect against truncate.
*/
i_mmap_unlock_read(vma->vm_file->f_mapping);
}
return ret;
uncharge_out:
mem_cgroup_cancel_charge(new_page, memcg);
page_cache_release(new_page);
return ret;
}
static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
struct page *fault_page;
struct address_space *mapping;
spinlock_t *ptl;
pte_t *pte;
int dirtied = 0;
int ret, tmp;
ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
return ret;
/*
* Check if the backing address space wants to know that the page is
* about to become writable
*/
if (vma->vm_ops->page_mkwrite) {
unlock_page(fault_page);
tmp = do_page_mkwrite(vma, fault_page, address);
if (unlikely(!tmp ||
(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
page_cache_release(fault_page);
return tmp;
}
}
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
if (unlikely(!pte_same(*pte, orig_pte))) {
pte_unmap_unlock(pte, ptl);
unlock_page(fault_page);
page_cache_release(fault_page);
return ret;
}
do_set_pte(vma, address, fault_page, pte, true, false);
pte_unmap_unlock(pte, ptl);
if (set_page_dirty(fault_page))
dirtied = 1;
/*
* Take a local copy of the address_space - page.mapping may be zeroed
* by truncate after unlock_page(). The address_space itself remains
* pinned by vma->vm_file's reference. We rely on unlock_page()'s
* release semantics to prevent the compiler from undoing this copying.
*/
mapping = fault_page->mapping;
unlock_page(fault_page);
if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
/*
* Some device drivers do not set page.mapping but still
* dirty their pages
*/
balance_dirty_pages_ratelimited(mapping);
}
if (!vma->vm_ops->page_mkwrite)
file_update_time(vma->vm_file);
return ret;
}
/*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults).
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
unsigned int flags, pte_t orig_pte)
{
pgoff_t pgoff = (((address & PAGE_MASK)
- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
pte_unmap(page_table);
/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
if (!vma->vm_ops->fault)
return VM_FAULT_SIGBUS;
if (!(flags & FAULT_FLAG_WRITE))
return do_read_fault(mm, vma, address, pmd, pgoff, flags,
orig_pte);
if (!(vma->vm_flags & VM_SHARED))
return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
orig_pte);
return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}
static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
unsigned long addr, int page_nid,
int *flags)
{
get_page(page);
count_vm_numa_event(NUMA_HINT_FAULTS);
if (page_nid == numa_node_id()) {
count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
*flags |= TNF_FAULT_LOCAL;
}
return mpol_misplaced(page, vma, addr);
}
static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
{
struct page *page = NULL;
spinlock_t *ptl;
int page_nid = -1;
int last_cpupid;
int target_nid;
bool migrated = false;
bool was_writable = pte_write(pte);
int flags = 0;
/* A PROT_NONE fault should not end up here */
BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
/*
* The "pte" at this point cannot be used safely without
* validation through pte_unmap_same(). It's of NUMA type but
* the pfn may be screwed if the read is non atomic.
*
* We can safely just do a "set_pte_at()", because the old
* page table entry is not accessible, so there would be no
* concurrent hardware modifications to the PTE.
*/
ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
if (unlikely(!pte_same(*ptep, pte))) {
pte_unmap_unlock(ptep, ptl);
goto out;
}
/* Make it present again */
pte = pte_modify(pte, vma->vm_page_prot);
pte = pte_mkyoung(pte);
if (was_writable)
pte = pte_mkwrite(pte);
set_pte_at(mm, addr, ptep, pte);
update_mmu_cache(vma, addr, ptep);
page = vm_normal_page(vma, addr, pte);
if (!page) {
pte_unmap_unlock(ptep, ptl);
return 0;
}
/*
* Avoid grouping on RO pages in general. RO pages shouldn't hurt as
* much anyway since they can be in shared cache state. This misses
* the case where a mapping is writable but the process never writes
* to it but pte_write gets cleared during protection updates and
* pte_dirty has unpredictable behaviour between PTE scan updates,
* background writeback, dirty balancing and application behaviour.
*/
if (!(vma->vm_flags & VM_WRITE))
flags |= TNF_NO_GROUP;
/*
* Flag if the page is shared between multiple address spaces. This
* is later used when determining whether to group tasks together
*/
if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
flags |= TNF_SHARED;
last_cpupid = page_cpupid_last(page);
page_nid = page_to_nid(page);
target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags);
pte_unmap_unlock(ptep, ptl);
if (target_nid == -1) {
put_page(page);
goto out;
}
/* Migrate to the requested node */
migrated = migrate_misplaced_page(page, vma, target_nid);
if (migrated) {
page_nid = target_nid;
flags |= TNF_MIGRATED;
} else
flags |= TNF_MIGRATE_FAIL;
out:
if (page_nid != -1)
task_numa_fault(last_cpupid, page_nid, 1, flags);
return 0;
}
/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
* RISC architectures). The early dirtying is also good on the i386.
*
* There is also a hook called "update_mmu_cache()" that architectures
* with external mmu caches can use to update those (ie the Sparc or
* PowerPC hashed page tables that act as extended TLBs).
*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with pte unmapped and unlocked.
*
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
static int handle_pte_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pte_t *pte, pmd_t *pmd, unsigned int flags)
{
pte_t entry;
spinlock_t *ptl;
/*
* some architectures can have larger ptes than wordsize,
* e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and CONFIG_32BIT=y,
* so READ_ONCE or ACCESS_ONCE cannot guarantee atomic accesses.
* The code below just needs a consistent view for the ifs and
* we later double check anyway with the ptl lock held. So here
* a barrier will do.
*/
entry = *pte;
barrier();
if (!pte_present(entry)) {
if (pte_none(entry)) {
if (vma->vm_ops)
return do_fault(mm, vma, address, pte, pmd,
flags, entry);
return do_anonymous_page(mm, vma, address, pte, pmd,
flags);
}
return do_swap_page(mm, vma, address,
pte, pmd, flags, entry);
}
if (pte_protnone(entry))
return do_numa_page(mm, vma, address, entry, pte, pmd);
ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
if (unlikely(!pte_same(*pte, entry)))
goto unlock;
if (flags & FAULT_FLAG_WRITE) {
if (!pte_write(entry))
return do_wp_page(mm, vma, address,
pte, pmd, ptl, entry);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
update_mmu_cache(vma, address, pte);
} else {
/*
* This is needed only for protection faults but the arch code
* is not yet telling us if this is a protection fault or not.
* This still avoids useless tlb flushes for .text page faults
* with threads.
*/
if (flags & FAULT_FLAG_WRITE)
flush_tlb_fix_spurious_fault(vma, address);
}
unlock:
pte_unmap_unlock(pte, ptl);
return 0;
}
/*
* By the time we get here, we already hold the mm semaphore
*
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
if (unlikely(is_vm_hugetlb_page(vma)))
return hugetlb_fault(mm, vma, address, flags);
pgd = pgd_offset(mm, address);
pud = pud_alloc(mm, pgd, address);
if (!pud)
return VM_FAULT_OOM;
pmd = pmd_alloc(mm, pud, address);
if (!pmd)
return VM_FAULT_OOM;
if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
int ret = VM_FAULT_FALLBACK;
if (!vma->vm_ops)
ret = do_huge_pmd_anonymous_page(mm, vma, address,
pmd, flags);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
pmd_t orig_pmd = *pmd;
int ret;
barrier();
if (pmd_trans_huge(orig_pmd)) {
unsigned int dirty = flags & FAULT_FLAG_WRITE;
/*
* If the pmd is splitting, return and retry the
* the fault. Alternative: wait until the split
* is done, and goto retry.
*/
if (pmd_trans_splitting(orig_pmd))
return 0;
if (pmd_protnone(orig_pmd))
return do_huge_pmd_numa_page(mm, vma, address,
orig_pmd, pmd);
if (dirty && !pmd_write(orig_pmd)) {
ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
orig_pmd);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
huge_pmd_set_accessed(mm, vma, address, pmd,
orig_pmd, dirty);
return 0;
}
}
}
/*
* Use __pte_alloc instead of pte_alloc_map, because we can't
* run pte_offset_map on the pmd, if an huge pmd could
* materialize from under us from a different thread.
*/
if (unlikely(pmd_none(*pmd)) &&
unlikely(__pte_alloc(mm, vma, pmd, address)))
return VM_FAULT_OOM;
/* if an huge pmd materialized from under us just retry later */
if (unlikely(pmd_trans_huge(*pmd)))
return 0;
/*
* A regular pmd is established and it can't morph into a huge pmd
* from under us anymore at this point because we hold the mmap_sem
* read mode and khugepaged takes it in write mode. So now it's
* safe to run pte_offset_map().
*/
pte = pte_offset_map(pmd, address);
return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}
/*
* By the time we get here, we already hold the mm semaphore
*
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
*/
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
{
int ret;
__set_current_state(TASK_RUNNING);
count_vm_event(PGFAULT);
mem_cgroup_count_vm_event(mm, PGFAULT);
/* do counter updates before entering really critical section. */
check_sync_rss_stat(current);
/*
* Enable the memcg OOM handling for faults triggered in user
* space. Kernel faults are handled more gracefully.
*/
if (flags & FAULT_FLAG_USER)
mem_cgroup_oom_enable();
ret = __handle_mm_fault(mm, vma, address, flags);
if (flags & FAULT_FLAG_USER) {
mem_cgroup_oom_disable();
/*
* The task may have entered a memcg OOM situation but
* if the allocation error was handled gracefully (no
* VM_FAULT_OOM), there is no need to kill anything.
* Just clean up the OOM state peacefully.
*/
if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
mem_cgroup_oom_synchronize(false);
}
return ret;
}
EXPORT_SYMBOL_GPL(handle_mm_fault);
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
* We've already handled the fast-path in-line.
*/
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
pud_t *new = pud_alloc_one(mm, address);
if (!new)
return -ENOMEM;
smp_wmb(); /* See comment in __pte_alloc */
spin_lock(&mm->page_table_lock);
if (pgd_present(*pgd)) /* Another has populated it */
pud_free(mm, new);
else
pgd_populate(mm, pgd, new);
spin_unlock(&mm->page_table_lock);
return 0;
}
#endif /* __PAGETABLE_PUD_FOLDED */
#ifndef __PAGETABLE_PMD_FOLDED
/*
* Allocate page middle directory.
* We've already handled the fast-path in-line.
*/
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
pmd_t *new = pmd_alloc_one(mm, address);
if (!new)
return -ENOMEM;
smp_wmb(); /* See comment in __pte_alloc */
spin_lock(&mm->page_table_lock);
#ifndef __ARCH_HAS_4LEVEL_HACK
if (!pud_present(*pud)) {
mm_inc_nr_pmds(mm);
pud_populate(mm, pud, new);
} else /* Another has populated it */
pmd_free(mm, new);
#else
if (!pgd_present(*pud)) {
mm_inc_nr_pmds(mm);
pgd_populate(mm, pud, new);
} else /* Another has populated it */
pmd_free(mm, new);
#endif /* __ARCH_HAS_4LEVEL_HACK */
spin_unlock(&mm->page_table_lock);
return 0;
}
#endif /* __PAGETABLE_PMD_FOLDED */
static int __follow_pte(struct mm_struct *mm, unsigned long address,
pte_t **ptepp, spinlock_t **ptlp)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep;
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
goto out;
pud = pud_offset(pgd, address);
if (pud_none(*pud) || unlikely(pud_bad(*pud)))
goto out;
pmd = pmd_offset(pud, address);
VM_BUG_ON(pmd_trans_huge(*pmd));
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
goto out;
/* We cannot handle huge page PFN maps. Luckily they don't exist. */
if (pmd_huge(*pmd))
goto out;
ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
if (!ptep)
goto out;
if (!pte_present(*ptep))
goto unlock;
*ptepp = ptep;
return 0;
unlock:
pte_unmap_unlock(ptep, *ptlp);
out:
return -EINVAL;
}
static inline int follow_pte(struct mm_struct *mm, unsigned long address,
pte_t **ptepp, spinlock_t **ptlp)
{
int res;
/* (void) is needed to make gcc happy */
(void) __cond_lock(*ptlp,
!(res = __follow_pte(mm, address, ptepp, ptlp)));
return res;
}
/**
* follow_pfn - look up PFN at a user virtual address
* @vma: memory mapping
* @address: user virtual address
* @pfn: location to store found PFN
*
* Only IO mappings and raw PFN mappings are allowed.
*
* Returns zero and the pfn at @pfn on success, -ve otherwise.
*/
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
unsigned long *pfn)
{
int ret = -EINVAL;
spinlock_t *ptl;
pte_t *ptep;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
return ret;
ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
if (ret)
return ret;
*pfn = pte_pfn(*ptep);
pte_unmap_unlock(ptep, ptl);
return 0;
}
EXPORT_SYMBOL(follow_pfn);
#ifdef CONFIG_HAVE_IOREMAP_PROT
int follow_phys(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
unsigned long *prot, resource_size_t *phys)
{
int ret = -EINVAL;
pte_t *ptep, pte;
spinlock_t *ptl;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
goto out;
if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
goto out;
pte = *ptep;
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
*prot = pgprot_val(pte_pgprot(pte));
*phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
ret = 0;
unlock:
pte_unmap_unlock(ptep, ptl);
out:
return ret;
}
int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write)
{
resource_size_t phys_addr;
unsigned long prot = 0;
void __iomem *maddr;
int offset = addr & (PAGE_SIZE-1);
if (follow_phys(vma, addr, write, &prot, &phys_addr))
return -EINVAL;
maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
if (write)
memcpy_toio(maddr + offset, buf, len);
else
memcpy_fromio(buf, maddr + offset, len);
iounmap(maddr);
return len;
}
EXPORT_SYMBOL_GPL(generic_access_phys);
#endif
/*
* Access another process' address space as given in mm. If non-NULL, use the
* given task for page fault accounting.
*/
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
unsigned long addr, void *buf, int len, int write)
{
struct vm_area_struct *vma;
void *old_buf = buf;
down_read(&mm->mmap_sem);
/* ignore errors, just check how much was successfully transferred */
while (len) {
int bytes, ret, offset;
void *maddr;
struct page *page = NULL;
ret = get_user_pages(tsk, mm, addr, 1,
write, 1, &page, &vma);
if (ret <= 0) {
#ifndef CONFIG_HAVE_IOREMAP_PROT
break;
#else
/*
* Check if this is a VM_IO | VM_PFNMAP VMA, which
* we can access using slightly different code.
*/
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
break;
if (vma->vm_ops && vma->vm_ops->access)
ret = vma->vm_ops->access(vma, addr, buf,
len, write);
if (ret <= 0)
break;
bytes = ret;
#endif
} else {
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);
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);
return buf - old_buf;
}
/**
* access_remote_vm - access another process' address space
* @mm: the mm_struct of the target address space
* @addr: start address to access
* @buf: source or destination buffer
* @len: number of bytes to transfer
* @write: whether the access is a write
*
* The caller must hold a reference on @mm.
*/
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
void *buf, int len, int write)
{
return __access_remote_vm(NULL, mm, addr, buf, len, write);
}
/*
* Access another process' address space.
* Source/target buffer must be kernel space,
* Do not walk the page table directly, use get_user_pages
*/
int access_process_vm(struct task_struct *tsk, unsigned long addr,
void *buf, int len, int write)
{
struct mm_struct *mm;
int ret;
mm = get_task_mm(tsk);
if (!mm)
return 0;
ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
mmput(mm);
return ret;
}
/*
* Print the name of a VMA.
*/
void print_vma_addr(char *prefix, unsigned long ip)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
/*
* Do not print if we are in atomic
* contexts (in exception stacks, etc.):
*/
if (preempt_count())
return;
down_read(&mm->mmap_sem);
vma = find_vma(mm, ip);
if (vma && vma->vm_file) {
struct file *f = vma->vm_file;
char *buf = (char *)__get_free_page(GFP_KERNEL);
if (buf) {
char *p;
p = file_path(f, buf, PAGE_SIZE);
if (IS_ERR(p))
p = "?";
printk("%s%s[%lx+%lx]", prefix, kbasename(p),
vma->vm_start,
vma->vm_end - vma->vm_start);
free_page((unsigned long)buf);
}
}
up_read(&mm->mmap_sem);
}
#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)
void __might_fault(const char *file, int line)
{
/*
* Some code (nfs/sunrpc) uses socket ops on kernel memory while
* holding the mmap_sem, this is safe because kernel memory doesn't
* get paged out, therefore we'll never actually fault, and the
* below annotations will generate false positives.
*/
if (segment_eq(get_fs(), KERNEL_DS))
return;
if (pagefault_disabled())
return;
__might_sleep(file, line, 0);
#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
if (current->mm)
might_lock_read(¤t->mm->mmap_sem);
#endif
}
EXPORT_SYMBOL(__might_fault);
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
static void clear_gigantic_page(struct page *page,
unsigned long addr,
unsigned int pages_per_huge_page)
{
int i;
struct page *p = page;
might_sleep();
for (i = 0; i < pages_per_huge_page;
i++, p = mem_map_next(p, page, i)) {
cond_resched();
clear_user_highpage(p, addr + i * PAGE_SIZE);
}
}
void clear_huge_page(struct page *page,
unsigned long addr, unsigned int pages_per_huge_page)
{
int i;
if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
clear_gigantic_page(page, addr, pages_per_huge_page);
return;
}
might_sleep();
for (i = 0; i < pages_per_huge_page; i++) {
cond_resched();
clear_user_highpage(page + i, addr + i * PAGE_SIZE);
}
}
static void copy_user_gigantic_page(struct page *dst, struct page *src,
unsigned long addr,
struct vm_area_struct *vma,
unsigned int pages_per_huge_page)
{
int i;
struct page *dst_base = dst;
struct page *src_base = src;
for (i = 0; i < pages_per_huge_page; ) {
cond_resched();
copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
i++;
dst = mem_map_next(dst, dst_base, i);
src = mem_map_next(src, src_base, i);
}
}
void copy_user_huge_page(struct page *dst, struct page *src,
unsigned long addr, struct vm_area_struct *vma,
unsigned int pages_per_huge_page)
{
int i;
if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
copy_user_gigantic_page(dst, src, addr, vma,
pages_per_huge_page);
return;
}
might_sleep();
for (i = 0; i < pages_per_huge_page; i++) {
cond_resched();
copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
}
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
static struct kmem_cache *page_ptl_cachep;
void __init ptlock_cache_init(void)
{
page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
SLAB_PANIC, NULL);
}
bool ptlock_alloc(struct page *page)
{
spinlock_t *ptl;
ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL);
if (!ptl)
return false;
page->ptl = ptl;
return true;
}
void ptlock_free(struct page *page)
{
kmem_cache_free(page_ptl_cachep, page->ptl);
}
#endif
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/memory_hotplug.c
/*
* linux/mm/memory_hotplug.c
*
* Copyright (C)
*/
#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/highmem.h>
#include <linux/vmalloc.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/mm_inline.h>
#include <linux/firmware-map.h>
#include <linux/stop_machine.h>
#include <linux/hugetlb.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <asm/tlbflush.h>
#include "internal.h"
/*
* online_page_callback contains pointer to current page onlining function.
* Initially it is generic_online_page(). If it is required it could be
* changed by calling set_online_page_callback() for callback registration
* and restore_online_page_callback() for generic callback restore.
*/
static void generic_online_page(struct page *page);
static online_page_callback_t online_page_callback = generic_online_page;
static DEFINE_MUTEX(online_page_callback_lock);
/* The same as the cpu_hotplug lock, but for memory hotplug. */
static struct {
struct task_struct *active_writer;
struct mutex lock; /* Synchronizes accesses to refcount, */
/*
* Also blocks the new readers during
* an ongoing mem hotplug operation.
*/
int refcount;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
} mem_hotplug = {
.active_writer = NULL,
.lock = __MUTEX_INITIALIZER(mem_hotplug.lock),
.refcount = 0,
#ifdef CONFIG_DEBUG_LOCK_ALLOC
.dep_map = {.name = "mem_hotplug.lock" },
#endif
};
/* Lockdep annotations for get/put_online_mems() and mem_hotplug_begin/end() */
#define memhp_lock_acquire_read() lock_map_acquire_read(&mem_hotplug.dep_map)
#define memhp_lock_acquire() lock_map_acquire(&mem_hotplug.dep_map)
#define memhp_lock_release() lock_map_release(&mem_hotplug.dep_map)
void get_online_mems(void)
{
might_sleep();
if (mem_hotplug.active_writer == current)
return;
memhp_lock_acquire_read();
mutex_lock(&mem_hotplug.lock);
mem_hotplug.refcount++;
mutex_unlock(&mem_hotplug.lock);
}
void put_online_mems(void)
{
if (mem_hotplug.active_writer == current)
return;
mutex_lock(&mem_hotplug.lock);
if (WARN_ON(!mem_hotplug.refcount))
mem_hotplug.refcount++; /* try to fix things up */
if (!--mem_hotplug.refcount && unlikely(mem_hotplug.active_writer))
wake_up_process(mem_hotplug.active_writer);
mutex_unlock(&mem_hotplug.lock);
memhp_lock_release();
}
void mem_hotplug_begin(void)
{
mem_hotplug.active_writer = current;
memhp_lock_acquire();
for (;;) {
mutex_lock(&mem_hotplug.lock);
if (likely(!mem_hotplug.refcount))
break;
__set_current_state(TASK_UNINTERRUPTIBLE);
mutex_unlock(&mem_hotplug.lock);
schedule();
}
}
void mem_hotplug_done(void)
{
mem_hotplug.active_writer = NULL;
mutex_unlock(&mem_hotplug.lock);
memhp_lock_release();
}
/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
struct resource *res;
res = kzalloc(sizeof(struct resource), GFP_KERNEL);
BUG_ON(!res);
res->name = "System RAM";
res->start = start;
res->end = start + size - 1;
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
if (request_resource(&iomem_resource, res) < 0) {
pr_debug("System RAM resource %pR cannot be added\n", res);
kfree(res);
res = NULL;
}
return res;
}
static void release_memory_resource(struct resource *res)
{
if (!res)
return;
release_resource(res);
kfree(res);
return;
}
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
void get_page_bootmem(unsigned long info, struct page *page,
unsigned long type)
{
page->lru.next = (struct list_head *) type;
SetPagePrivate(page);
set_page_private(page, info);
atomic_inc(&page->_count);
}
void put_page_bootmem(struct page *page)
{
unsigned long type;
type = (unsigned long) page->lru.next;
BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
if (atomic_dec_return(&page->_count) == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
INIT_LIST_HEAD(&page->lru);
free_reserved_page(page);
}
}
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
#ifndef CONFIG_SPARSEMEM_VMEMMAP
static void register_page_bootmem_info_section(unsigned long start_pfn)
{
unsigned long *usemap, mapsize, section_nr, i;
struct mem_section *ms;
struct page *page, *memmap;
section_nr = pfn_to_section_nr(start_pfn);
ms = __nr_to_section(section_nr);
/* Get section's memmap address */
memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
/*
* Get page for the memmap's phys address
* XXX: need more consideration for sparse_vmemmap...
*/
page = virt_to_page(memmap);
mapsize = sizeof(struct page) * PAGES_PER_SECTION;
mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
/* remember memmap's page */
for (i = 0; i < mapsize; i++, page++)
get_page_bootmem(section_nr, page, SECTION_INFO);
usemap = __nr_to_section(section_nr)->pageblock_flags;
page = virt_to_page(usemap);
mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
for (i = 0; i < mapsize; i++, page++)
get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
}
#else /* CONFIG_SPARSEMEM_VMEMMAP */
static void register_page_bootmem_info_section(unsigned long start_pfn)
{
unsigned long *usemap, mapsize, section_nr, i;
struct mem_section *ms;
struct page *page, *memmap;
if (!pfn_valid(start_pfn))
return;
section_nr = pfn_to_section_nr(start_pfn);
ms = __nr_to_section(section_nr);
memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
usemap = __nr_to_section(section_nr)->pageblock_flags;
page = virt_to_page(usemap);
mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
for (i = 0; i < mapsize; i++, page++)
get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
unsigned long i, pfn, end_pfn, nr_pages;
int node = pgdat->node_id;
struct page *page;
struct zone *zone;
nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
page = virt_to_page(pgdat);
for (i = 0; i < nr_pages; i++, page++)
get_page_bootmem(node, page, NODE_INFO);
zone = &pgdat->node_zones[0];
for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
if (zone_is_initialized(zone)) {
nr_pages = zone->wait_table_hash_nr_entries
* sizeof(wait_queue_head_t);
nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
page = virt_to_page(zone->wait_table);
for (i = 0; i < nr_pages; i++, page++)
get_page_bootmem(node, page, NODE_INFO);
}
}
pfn = pgdat->node_start_pfn;
end_pfn = pgdat_end_pfn(pgdat);
/* register section info */
for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
/*
* Some platforms can assign the same pfn to multiple nodes - on
* node0 as well as nodeN. To avoid registering a pfn against
* multiple nodes we check that this pfn does not already
* reside in some other nodes.
*/
if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
register_page_bootmem_info_section(pfn);
}
}
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
static void __meminit grow_zone_span(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long old_zone_end_pfn;
zone_span_writelock(zone);
old_zone_end_pfn = zone_end_pfn(zone);
if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn)
zone->zone_start_pfn = start_pfn;
zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
zone->zone_start_pfn;
zone_span_writeunlock(zone);
}
static void resize_zone(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
zone_span_writelock(zone);
if (end_pfn - start_pfn) {
zone->zone_start_pfn = start_pfn;
zone->spanned_pages = end_pfn - start_pfn;
} else {
/*
* make it consist as free_area_init_core(),
* if spanned_pages = 0, then keep start_pfn = 0
*/
zone->zone_start_pfn = 0;
zone->spanned_pages = 0;
}
zone_span_writeunlock(zone);
}
static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
enum zone_type zid = zone_idx(zone);
int nid = zone->zone_pgdat->node_id;
unsigned long pfn;
for (pfn = start_pfn; pfn < end_pfn; pfn++)
set_page_links(pfn_to_page(pfn), zid, nid, pfn);
}
/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
* alloc_bootmem_node_nopanic()/memblock_virt_alloc_node_nopanic() */
static int __ref ensure_zone_is_initialized(struct zone *zone,
unsigned long start_pfn, unsigned long num_pages)
{
if (!zone_is_initialized(zone))
return init_currently_empty_zone(zone, start_pfn, num_pages,
MEMMAP_HOTPLUG);
return 0;
}
static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
unsigned long start_pfn, unsigned long end_pfn)
{
int ret;
unsigned long flags;
unsigned long z1_start_pfn;
ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn);
if (ret)
return ret;
pgdat_resize_lock(z1->zone_pgdat, &flags);
/* can't move pfns which are higher than @z2 */
if (end_pfn > zone_end_pfn(z2))
goto out_fail;
/* the move out part must be at the left most of @z2 */
if (start_pfn > z2->zone_start_pfn)
goto out_fail;
/* must included/overlap */
if (end_pfn <= z2->zone_start_pfn)
goto out_fail;
/* use start_pfn for z1's start_pfn if z1 is empty */
if (!zone_is_empty(z1))
z1_start_pfn = z1->zone_start_pfn;
else
z1_start_pfn = start_pfn;
resize_zone(z1, z1_start_pfn, end_pfn);
resize_zone(z2, end_pfn, zone_end_pfn(z2));
pgdat_resize_unlock(z1->zone_pgdat, &flags);
fix_zone_id(z1, start_pfn, end_pfn);
return 0;
out_fail:
pgdat_resize_unlock(z1->zone_pgdat, &flags);
return -1;
}
static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
unsigned long start_pfn, unsigned long end_pfn)
{
int ret;
unsigned long flags;
unsigned long z2_end_pfn;
ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn);
if (ret)
return ret;
pgdat_resize_lock(z1->zone_pgdat, &flags);
/* can't move pfns which are lower than @z1 */
if (z1->zone_start_pfn > start_pfn)
goto out_fail;
/* the move out part mast at the right most of @z1 */
if (zone_end_pfn(z1) > end_pfn)
goto out_fail;
/* must included/overlap */
if (start_pfn >= zone_end_pfn(z1))
goto out_fail;
/* use end_pfn for z2's end_pfn if z2 is empty */
if (!zone_is_empty(z2))
z2_end_pfn = zone_end_pfn(z2);
else
z2_end_pfn = end_pfn;
resize_zone(z1, z1->zone_start_pfn, start_pfn);
resize_zone(z2, start_pfn, z2_end_pfn);
pgdat_resize_unlock(z1->zone_pgdat, &flags);
fix_zone_id(z2, start_pfn, end_pfn);
return 0;
out_fail:
pgdat_resize_unlock(z1->zone_pgdat, &flags);
return -1;
}
static void __meminit grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat);
if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
pgdat->node_start_pfn = start_pfn;
pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
pgdat->node_start_pfn;
}
static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int nr_pages = PAGES_PER_SECTION;
int nid = pgdat->node_id;
int zone_type;
unsigned long flags, pfn;
int ret;
zone_type = zone - pgdat->node_zones;
ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages);
if (ret)
return ret;
pgdat_resize_lock(zone->zone_pgdat, &flags);
grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages);
grow_pgdat_span(zone->zone_pgdat, phys_start_pfn,
phys_start_pfn + nr_pages);
pgdat_resize_unlock(zone->zone_pgdat, &flags);
memmap_init_zone(nr_pages, nid, zone_type,
phys_start_pfn, MEMMAP_HOTPLUG);
/* online_page_range is called later and expects pages reserved */
for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) {
if (!pfn_valid(pfn))
continue;
SetPageReserved(pfn_to_page(pfn));
}
return 0;
}
static int __meminit __add_section(int nid, struct zone *zone,
unsigned long phys_start_pfn)
{
int ret;
if (pfn_valid(phys_start_pfn))
return -EEXIST;
ret = sparse_add_one_section(zone, phys_start_pfn);
if (ret < 0)
return ret;
ret = __add_zone(zone, phys_start_pfn);
if (ret < 0)
return ret;
return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
}
/*
* Reasonably generic function for adding memory. It is
* expected that archs that support memory hotplug will
* call this function after deciding the zone to which to
* add the new pages.
*/
int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
unsigned long nr_pages)
{
unsigned long i;
int err = 0;
int start_sec, end_sec;
/* during initialize mem_map, align hot-added range to section */
start_sec = pfn_to_section_nr(phys_start_pfn);
end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
for (i = start_sec; i <= end_sec; i++) {
err = __add_section(nid, zone, section_nr_to_pfn(i));
/*
* EEXIST is finally dealt with by ioresource collision
* check. see add_memory() => register_memory_resource()
* Warning will be printed if there is collision.
*/
if (err && (err != -EEXIST))
break;
err = 0;
}
vmemmap_populate_print_last();
return err;
}
EXPORT_SYMBOL_GPL(__add_pages);
#ifdef CONFIG_MEMORY_HOTREMOVE
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static int find_smallest_section_pfn(int nid, struct zone *zone,
unsigned long start_pfn,
unsigned long end_pfn)
{
struct mem_section *ms;
for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
ms = __pfn_to_section(start_pfn);
if (unlikely(!valid_section(ms)))
continue;
if (unlikely(pfn_to_nid(start_pfn) != nid))
continue;
if (zone && zone != page_zone(pfn_to_page(start_pfn)))
continue;
return start_pfn;
}
return 0;
}
/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
static int find_biggest_section_pfn(int nid, struct zone *zone,
unsigned long start_pfn,
unsigned long end_pfn)
{
struct mem_section *ms;
unsigned long pfn;
/* pfn is the end pfn of a memory section. */
pfn = end_pfn - 1;
for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
ms = __pfn_to_section(pfn);
if (unlikely(!valid_section(ms)))
continue;
if (unlikely(pfn_to_nid(pfn) != nid))
continue;
if (zone && zone != page_zone(pfn_to_page(pfn)))
continue;
return pfn;
}
return 0;
}
static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long zone_start_pfn = zone->zone_start_pfn;
unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
unsigned long zone_end_pfn = z;
unsigned long pfn;
struct mem_section *ms;
int nid = zone_to_nid(zone);
zone_span_writelock(zone);
if (zone_start_pfn == start_pfn) {
/*
* If the section is smallest section in the zone, it need
* shrink zone->zone_start_pfn and zone->zone_spanned_pages.
* In this case, we find second smallest valid mem_section
* for shrinking zone.
*/
pfn = find_smallest_section_pfn(nid, zone, end_pfn,
zone_end_pfn);
if (pfn) {
zone->zone_start_pfn = pfn;
zone->spanned_pages = zone_end_pfn - pfn;
}
} else if (zone_end_pfn == end_pfn) {
/*
* If the section is biggest section in the zone, it need
* shrink zone->spanned_pages.
* In this case, we find second biggest valid mem_section for
* shrinking zone.
*/
pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
start_pfn);
if (pfn)
zone->spanned_pages = pfn - zone_start_pfn + 1;
}
/*
* The section is not biggest or smallest mem_section in the zone, it
* only creates a hole in the zone. So in this case, we need not
* change the zone. But perhaps, the zone has only hole data. Thus
* it check the zone has only hole or not.
*/
pfn = zone_start_pfn;
for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
ms = __pfn_to_section(pfn);
if (unlikely(!valid_section(ms)))
continue;
if (page_zone(pfn_to_page(pfn)) != zone)
continue;
/* If the section is current section, it continues the loop */
if (start_pfn == pfn)
continue;
/* If we find valid section, we have nothing to do */
zone_span_writeunlock(zone);
return;
}
/* The zone has no valid section */
zone->zone_start_pfn = 0;
zone->spanned_pages = 0;
zone_span_writeunlock(zone);
}
static void shrink_pgdat_span(struct pglist_data *pgdat,
unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
unsigned long pgdat_end_pfn = p;
unsigned long pfn;
struct mem_section *ms;
int nid = pgdat->node_id;
if (pgdat_start_pfn == start_pfn) {
/*
* If the section is smallest section in the pgdat, it need
* shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
* In this case, we find second smallest valid mem_section
* for shrinking zone.
*/
pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
pgdat_end_pfn);
if (pfn) {
pgdat->node_start_pfn = pfn;
pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
}
} else if (pgdat_end_pfn == end_pfn) {
/*
* If the section is biggest section in the pgdat, it need
* shrink pgdat->node_spanned_pages.
* In this case, we find second biggest valid mem_section for
* shrinking zone.
*/
pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
start_pfn);
if (pfn)
pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
}
/*
* If the section is not biggest or smallest mem_section in the pgdat,
* it only creates a hole in the pgdat. So in this case, we need not
* change the pgdat.
* But perhaps, the pgdat has only hole data. Thus it check the pgdat
* has only hole or not.
*/
pfn = pgdat_start_pfn;
for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
ms = __pfn_to_section(pfn);
if (unlikely(!valid_section(ms)))
continue;
if (pfn_to_nid(pfn) != nid)
continue;
/* If the section is current section, it continues the loop */
if (start_pfn == pfn)
continue;
/* If we find valid section, we have nothing to do */
return;
}
/* The pgdat has no valid section */
pgdat->node_start_pfn = 0;
pgdat->node_spanned_pages = 0;
}
static void __remove_zone(struct zone *zone, unsigned long start_pfn)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int nr_pages = PAGES_PER_SECTION;
int zone_type;
unsigned long flags;
zone_type = zone - pgdat->node_zones;
pgdat_resize_lock(zone->zone_pgdat, &flags);
shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
pgdat_resize_unlock(zone->zone_pgdat, &flags);
}
mm6.txt
最新推荐文章于 2024-09-10 10:21:38 发布