*/
#include <linux/migrate.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/memcontrol.h>
#include <linux/syscalls.h>
#include <linux/hugetlb.h>
+#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
+#include <linux/balloon_compaction.h>
#include <asm/tlbflush.h>
-#include "internal.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/migrate.h>
-#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
+#include "internal.h"
/*
* migrate_prep() needs to be called before we start compiling a list of pages
list_del(&page->lru);
dec_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
- putback_lru_page(page);
+ putback_lru_page(page);
+ }
+}
+
+/*
+ * Put previously isolated pages back onto the appropriate lists
+ * from where they were once taken off for compaction/migration.
+ *
+ * This function shall be used instead of putback_lru_pages(),
+ * whenever the isolated pageset has been built by isolate_migratepages_range()
+ */
+void putback_movable_pages(struct list_head *l)
+{
+ struct page *page;
+ struct page *page2;
+
+ list_for_each_entry_safe(page, page2, l, lru) {
+ list_del(&page->lru);
+ dec_zone_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_cache(page));
+ if (unlikely(isolated_balloon_page(page)))
+ balloon_page_putback(page);
+ else
+ putback_lru_page(page);
}
}
{
struct mm_struct *mm = vma->vm_mm;
swp_entry_t entry;
- pgd_t *pgd;
- pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
spinlock_t *ptl;
goto out;
ptl = &mm->page_table_lock;
} else {
- pgd = pgd_offset(mm, addr);
- if (!pgd_present(*pgd))
+ pmd = mm_find_pmd(mm, addr);
+ if (!pmd)
goto out;
-
- pud = pud_offset(pgd, addr);
- if (!pud_present(*pud))
- goto out;
-
- pmd = pmd_offset(pud, addr);
if (pmd_trans_huge(*pmd))
goto out;
- if (!pmd_present(*pmd))
- goto out;
ptep = pte_offset_map(pmd, addr);
- if (!is_swap_pte(*ptep)) {
- pte_unmap(ptep);
- goto out;
- }
+ /*
+ * Peek to check is_swap_pte() before taking ptlock? No, we
+ * can race mremap's move_ptes(), which skips anon_vma lock.
+ */
ptl = pte_lockptr(mm, pmd);
}
if (is_write_migration_entry(entry))
pte = pte_mkwrite(pte);
#ifdef CONFIG_HUGETLB_PAGE
- if (PageHuge(new))
+ if (PageHuge(new)) {
pte = pte_mkhuge(pte);
+ pte = arch_make_huge_pte(pte, vma, new, 0);
+ }
#endif
- flush_cache_page(vma, addr, pte_pfn(pte));
+ flush_dcache_page(new);
set_pte_at(mm, addr, ptep, pte);
if (PageHuge(new)) {
* Something used the pte of a page under migration. We need to
* get to the page and wait until migration is finished.
* When we return from this function the fault will be retried.
- *
- * This function is called from do_swap_page().
*/
-void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
- unsigned long address)
+static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+ spinlock_t *ptl)
{
- pte_t *ptep, pte;
- spinlock_t *ptl;
+ pte_t pte;
swp_entry_t entry;
struct page *page;
- ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+ spin_lock(ptl);
pte = *ptep;
if (!is_swap_pte(pte))
goto out;
pte_unmap_unlock(ptep, ptl);
}
+void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
+ unsigned long address)
+{
+ spinlock_t *ptl = pte_lockptr(mm, pmd);
+ pte_t *ptep = pte_offset_map(pmd, address);
+ __migration_entry_wait(mm, ptep, ptl);
+}
+
+void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+{
+ spinlock_t *ptl = &(mm)->page_table_lock;
+ __migration_entry_wait(mm, pte, ptl);
+}
+
+#ifdef CONFIG_BLOCK
+/* Returns true if all buffers are successfully locked */
+static bool buffer_migrate_lock_buffers(struct buffer_head *head,
+ enum migrate_mode mode)
+{
+ struct buffer_head *bh = head;
+
+ /* Simple case, sync compaction */
+ if (mode != MIGRATE_ASYNC) {
+ do {
+ get_bh(bh);
+ lock_buffer(bh);
+ bh = bh->b_this_page;
+
+ } while (bh != head);
+
+ return true;
+ }
+
+ /* async case, we cannot block on lock_buffer so use trylock_buffer */
+ do {
+ get_bh(bh);
+ if (!trylock_buffer(bh)) {
+ /*
+ * We failed to lock the buffer and cannot stall in
+ * async migration. Release the taken locks
+ */
+ struct buffer_head *failed_bh = bh;
+ put_bh(failed_bh);
+ bh = head;
+ while (bh != failed_bh) {
+ unlock_buffer(bh);
+ put_bh(bh);
+ bh = bh->b_this_page;
+ }
+ return false;
+ }
+
+ bh = bh->b_this_page;
+ } while (bh != head);
+ return true;
+}
+#else
+static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
+ enum migrate_mode mode)
+{
+ return true;
+}
+#endif /* CONFIG_BLOCK */
+
/*
* Replace the page in the mapping.
*
* 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
*/
static int migrate_page_move_mapping(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct page *newpage, struct page *page,
+ struct buffer_head *head, enum migrate_mode mode)
{
- int expected_count;
+ int expected_count = 0;
void **pslot;
if (!mapping) {
/* Anonymous page without mapping */
if (page_count(page) != 1)
return -EAGAIN;
- return 0;
+ return MIGRATEPAGE_SUCCESS;
}
spin_lock_irq(&mapping->tree_lock);
return -EAGAIN;
}
+ /*
+ * In the async migration case of moving a page with buffers, lock the
+ * buffers using trylock before the mapping is moved. If the mapping
+ * was moved, we later failed to lock the buffers and could not move
+ * the mapping back due to an elevated page count, we would have to
+ * block waiting on other references to be dropped.
+ */
+ if (mode == MIGRATE_ASYNC && head &&
+ !buffer_migrate_lock_buffers(head, mode)) {
+ page_unfreeze_refs(page, expected_count);
+ spin_unlock_irq(&mapping->tree_lock);
+ return -EAGAIN;
+ }
+
/*
* Now we know that no one else is looking at the page.
*/
radix_tree_replace_slot(pslot, newpage);
- page_unfreeze_refs(page, expected_count);
/*
- * Drop cache reference from old page.
+ * Drop cache reference from old page by unfreezing
+ * to one less reference.
* We know this isn't the last reference.
*/
- __put_page(page);
+ page_unfreeze_refs(page, expected_count - 1);
/*
* If moved to a different zone then also account
}
spin_unlock_irq(&mapping->tree_lock);
- return 0;
+ return MIGRATEPAGE_SUCCESS;
}
/*
if (!mapping) {
if (page_count(page) != 1)
return -EAGAIN;
- return 0;
+ return MIGRATEPAGE_SUCCESS;
}
spin_lock_irq(&mapping->tree_lock);
radix_tree_replace_slot(pslot, newpage);
- page_unfreeze_refs(page, expected_count);
-
- __put_page(page);
+ page_unfreeze_refs(page, expected_count - 1);
spin_unlock_irq(&mapping->tree_lock);
- return 0;
+ return MIGRATEPAGE_SUCCESS;
}
/*
*/
void migrate_page_copy(struct page *newpage, struct page *page)
{
- if (PageHuge(page))
+ if (PageHuge(page) || PageTransHuge(page))
copy_huge_page(newpage, page);
else
copy_highpage(newpage, page);
* is actually a signal that all of the page has become dirty.
* Whereas only part of our page may be dirty.
*/
- __set_page_dirty_nobuffers(newpage);
+ if (PageSwapBacked(page))
+ SetPageDirty(newpage);
+ else
+ __set_page_dirty_nobuffers(newpage);
}
mlock_migrate_page(newpage, page);
ksm_migrate_page(newpage, page);
-
+ /*
+ * Please do not reorder this without considering how mm/ksm.c's
+ * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
+ */
ClearPageSwapCache(page);
ClearPagePrivate(page);
set_page_private(page, 0);
- page->mapping = NULL;
/*
* If any waiters have accumulated on the new page then
* Pages are locked upon entry and exit.
*/
int migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
{
int rc;
BUG_ON(PageWriteback(page)); /* Writeback must be complete */
- rc = migrate_page_move_mapping(mapping, newpage, page);
+ rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
- if (rc)
+ if (rc != MIGRATEPAGE_SUCCESS)
return rc;
migrate_page_copy(newpage, page);
- return 0;
+ return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(migrate_page);
* exist.
*/
int buffer_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct page *newpage, struct page *page, enum migrate_mode mode)
{
struct buffer_head *bh, *head;
int rc;
if (!page_has_buffers(page))
- return migrate_page(mapping, newpage, page);
+ return migrate_page(mapping, newpage, page, mode);
head = page_buffers(page);
- rc = migrate_page_move_mapping(mapping, newpage, page);
+ rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
- if (rc)
+ if (rc != MIGRATEPAGE_SUCCESS)
return rc;
- bh = head;
- do {
- get_bh(bh);
- lock_buffer(bh);
- bh = bh->b_this_page;
-
- } while (bh != head);
+ /*
+ * In the async case, migrate_page_move_mapping locked the buffers
+ * with an IRQ-safe spinlock held. In the sync case, the buffers
+ * need to be locked now
+ */
+ if (mode != MIGRATE_ASYNC)
+ BUG_ON(!buffer_migrate_lock_buffers(head, mode));
ClearPagePrivate(page);
set_page_private(newpage, page_private(page));
} while (bh != head);
- return 0;
+ return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(buffer_migrate_page);
#endif
* Default handling if a filesystem does not provide a migration function.
*/
static int fallback_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct page *newpage, struct page *page, enum migrate_mode mode)
{
- if (PageDirty(page))
+ if (PageDirty(page)) {
+ /* Only writeback pages in full synchronous migration */
+ if (mode != MIGRATE_SYNC)
+ return -EBUSY;
return writeout(mapping, page);
+ }
/*
* Buffers may be managed in a filesystem specific way.
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
- return migrate_page(mapping, newpage, page);
+ return migrate_page(mapping, newpage, page, mode);
}
/*
*
* Return value:
* < 0 - error code
- * == 0 - success
+ * MIGRATEPAGE_SUCCESS - success
*/
static int move_to_new_page(struct page *newpage, struct page *page,
- int remap_swapcache, bool sync)
+ int remap_swapcache, enum migrate_mode mode)
{
struct address_space *mapping;
int rc;
mapping = page_mapping(page);
if (!mapping)
- rc = migrate_page(mapping, newpage, page);
- else {
+ rc = migrate_page(mapping, newpage, page, mode);
+ else if (mapping->a_ops->migratepage)
/*
- * Do not writeback pages if !sync and migratepage is
- * not pointing to migrate_page() which is nonblocking
- * (swapcache/tmpfs uses migratepage = migrate_page).
+ * Most pages have a mapping and most filesystems provide a
+ * migratepage callback. Anonymous pages are part of swap
+ * space which also has its own migratepage callback. This
+ * is the most common path for page migration.
*/
- if (PageDirty(page) && !sync &&
- mapping->a_ops->migratepage != migrate_page)
- rc = -EBUSY;
- else if (mapping->a_ops->migratepage)
- /*
- * Most pages have a mapping and most filesystems
- * should provide a migration function. Anonymous
- * pages are part of swap space which also has its
- * own migration function. This is the most common
- * path for page migration.
- */
- rc = mapping->a_ops->migratepage(mapping,
- newpage, page);
- else
- rc = fallback_migrate_page(mapping, newpage, page);
- }
+ rc = mapping->a_ops->migratepage(mapping,
+ newpage, page, mode);
+ else
+ rc = fallback_migrate_page(mapping, newpage, page, mode);
- if (rc) {
+ if (rc != MIGRATEPAGE_SUCCESS) {
newpage->mapping = NULL;
} else {
if (remap_swapcache)
remove_migration_ptes(page, newpage);
+ page->mapping = NULL;
}
unlock_page(newpage);
return rc;
}
-/*
- * Obtain the lock on page, remove all ptes and migrate the page
- * to the newly allocated page in newpage.
- */
-static int unmap_and_move(new_page_t get_new_page, unsigned long private,
- struct page *page, int force, bool offlining, bool sync)
+static int __unmap_and_move(struct page *page, struct page *newpage,
+ int force, enum migrate_mode mode)
{
- int rc = 0;
- int *result = NULL;
- struct page *newpage = get_new_page(page, private, &result);
+ int rc = -EAGAIN;
int remap_swapcache = 1;
- int charge = 0;
struct mem_cgroup *mem;
struct anon_vma *anon_vma = NULL;
- if (!newpage)
- return -ENOMEM;
-
- if (page_count(page) == 1) {
- /* page was freed from under us. So we are done. */
- goto move_newpage;
- }
- if (unlikely(PageTransHuge(page)))
- if (unlikely(split_huge_page(page)))
- goto move_newpage;
-
- /* prepare cgroup just returns 0 or -ENOMEM */
- rc = -EAGAIN;
-
if (!trylock_page(page)) {
- if (!force || !sync)
- goto move_newpage;
+ if (!force || mode == MIGRATE_ASYNC)
+ goto out;
/*
* It's not safe for direct compaction to call lock_page.
* altogether.
*/
if (current->flags & PF_MEMALLOC)
- goto move_newpage;
+ goto out;
lock_page(page);
}
- /*
- * Only memory hotplug's offline_pages() caller has locked out KSM,
- * and can safely migrate a KSM page. The other cases have skipped
- * PageKsm along with PageReserved - but it is only now when we have
- * the page lock that we can be certain it will not go KSM beneath us
- * (KSM will not upgrade a page from PageAnon to PageKsm when it sees
- * its pagecount raised, but only here do we take the page lock which
- * serializes that).
- */
- if (PageKsm(page) && !offlining) {
- rc = -EBUSY;
- goto unlock;
- }
-
/* charge against new page */
- charge = mem_cgroup_prepare_migration(page, newpage, &mem, GFP_KERNEL);
- if (charge == -ENOMEM) {
- rc = -ENOMEM;
- goto unlock;
- }
- BUG_ON(charge);
+ mem_cgroup_prepare_migration(page, newpage, &mem);
if (PageWriteback(page)) {
/*
- * For !sync, there is no point retrying as the retry loop
- * is expected to be too short for PageWriteback to be cleared
+ * Only in the case of a full synchronous migration is it
+ * necessary to wait for PageWriteback. In the async case,
+ * the retry loop is too short and in the sync-light case,
+ * the overhead of stalling is too much
*/
- if (!sync) {
+ if (mode != MIGRATE_SYNC) {
rc = -EBUSY;
goto uncharge;
}
* File Caches may use write_page() or lock_page() in migration, then,
* just care Anon page here.
*/
- if (PageAnon(page)) {
+ if (PageAnon(page) && !PageKsm(page)) {
/*
- * Only page_lock_anon_vma() understands the subtleties of
+ * Only page_lock_anon_vma_read() understands the subtleties of
* getting a hold on an anon_vma from outside one of its mms.
*/
anon_vma = page_get_anon_vma(page);
}
}
+ if (unlikely(balloon_page_movable(page))) {
+ /*
+ * A ballooned page does not need any special attention from
+ * physical to virtual reverse mapping procedures.
+ * Skip any attempt to unmap PTEs or to remap swap cache,
+ * in order to avoid burning cycles at rmap level, and perform
+ * the page migration right away (proteced by page lock).
+ */
+ rc = balloon_page_migrate(newpage, page, mode);
+ goto uncharge;
+ }
+
/*
* Corner case handling:
* 1. When a new swap-cache page is read into, it is added to the LRU
skip_unmap:
if (!page_mapped(page))
- rc = move_to_new_page(newpage, page, remap_swapcache, sync);
+ rc = move_to_new_page(newpage, page, remap_swapcache, mode);
if (rc && remap_swapcache)
remove_migration_ptes(page, page);
put_anon_vma(anon_vma);
uncharge:
- if (!charge)
- mem_cgroup_end_migration(mem, page, newpage, rc == 0);
-unlock:
+ mem_cgroup_end_migration(mem, page, newpage,
+ (rc == MIGRATEPAGE_SUCCESS ||
+ rc == MIGRATEPAGE_BALLOON_SUCCESS));
unlock_page(page);
+out:
+ return rc;
+}
-move_newpage:
+/*
+ * Obtain the lock on page, remove all ptes and migrate the page
+ * to the newly allocated page in newpage.
+ */
+static int unmap_and_move(new_page_t get_new_page, unsigned long private,
+ struct page *page, int force, enum migrate_mode mode)
+{
+ int rc = 0;
+ int *result = NULL;
+ struct page *newpage = get_new_page(page, private, &result);
+
+ if (!newpage)
+ return -ENOMEM;
+
+ if (page_count(page) == 1) {
+ /* page was freed from under us. So we are done. */
+ goto out;
+ }
+
+ if (unlikely(PageTransHuge(page)))
+ if (unlikely(split_huge_page(page)))
+ goto out;
+
+ rc = __unmap_and_move(page, newpage, force, mode);
+
+ if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) {
+ /*
+ * A ballooned page has been migrated already.
+ * Now, it's the time to wrap-up counters,
+ * handle the page back to Buddy and return.
+ */
+ dec_zone_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_cache(page));
+ balloon_page_free(page);
+ return MIGRATEPAGE_SUCCESS;
+ }
+out:
if (rc != -EAGAIN) {
- /*
- * A page that has been migrated has all references
- * removed and will be freed. A page that has not been
- * migrated will have kepts its references and be
- * restored.
- */
- list_del(&page->lru);
+ /*
+ * A page that has been migrated has all references
+ * removed and will be freed. A page that has not been
+ * migrated will have kepts its references and be
+ * restored.
+ */
+ list_del(&page->lru);
dec_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
putback_lru_page(page);
}
-
/*
* Move the new page to the LRU. If migration was not successful
* then this will free the page.
*/
putback_lru_page(newpage);
-
if (result) {
if (rc)
*result = rc;
*/
static int unmap_and_move_huge_page(new_page_t get_new_page,
unsigned long private, struct page *hpage,
- int force, bool offlining, bool sync)
+ int force, enum migrate_mode mode)
{
int rc = 0;
int *result = NULL;
rc = -EAGAIN;
if (!trylock_page(hpage)) {
- if (!force || !sync)
+ if (!force || mode != MIGRATE_SYNC)
goto out;
lock_page(hpage);
}
try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
if (!page_mapped(hpage))
- rc = move_to_new_page(new_hpage, hpage, 1, sync);
+ rc = move_to_new_page(new_hpage, hpage, 1, mode);
if (rc)
remove_migration_ptes(hpage, hpage);
if (anon_vma)
put_anon_vma(anon_vma);
-out:
- unlock_page(hpage);
- if (rc != -EAGAIN) {
- list_del(&hpage->lru);
- put_page(hpage);
- }
+ if (!rc)
+ hugetlb_cgroup_migrate(hpage, new_hpage);
+ unlock_page(hpage);
+out:
put_page(new_hpage);
-
if (result) {
if (rc)
*result = rc;
}
/*
- * migrate_pages
+ * migrate_pages - migrate the pages specified in a list, to the free pages
+ * supplied as the target for the page migration
*
- * The function takes one list of pages to migrate and a function
- * that determines from the page to be migrated and the private data
- * the target of the move and allocates the page.
+ * @from: The list of pages to be migrated.
+ * @get_new_page: The function used to allocate free pages to be used
+ * as the target of the page migration.
+ * @private: Private data to be passed on to get_new_page()
+ * @mode: The migration mode that specifies the constraints for
+ * page migration, if any.
+ * @reason: The reason for page migration.
*
- * The function returns after 10 attempts or if no pages
- * are movable anymore because to has become empty
- * or no retryable pages exist anymore.
- * Caller should call putback_lru_pages to return pages to the LRU
+ * The function returns after 10 attempts or if no pages are movable any more
+ * because the list has become empty or no retryable pages exist any more.
+ * The caller should call putback_lru_pages() to return pages to the LRU
* or free list only if ret != 0.
*
- * Return: Number of pages not migrated or error code.
+ * Returns the number of pages that were not migrated, or an error code.
*/
-int migrate_pages(struct list_head *from,
- new_page_t get_new_page, unsigned long private, bool offlining,
- bool sync)
+int migrate_pages(struct list_head *from, new_page_t get_new_page,
+ unsigned long private, enum migrate_mode mode, int reason)
{
int retry = 1;
int nr_failed = 0;
+ int nr_succeeded = 0;
int pass = 0;
struct page *page;
struct page *page2;
cond_resched();
rc = unmap_and_move(get_new_page, private,
- page, pass > 2, offlining,
- sync);
+ page, pass > 2, mode);
switch(rc) {
case -ENOMEM:
case -EAGAIN:
retry++;
break;
- case 0:
+ case MIGRATEPAGE_SUCCESS:
+ nr_succeeded++;
break;
default:
/* Permanent failure */
}
}
}
- rc = 0;
+ rc = nr_failed + retry;
out:
+ if (nr_succeeded)
+ count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
+ if (nr_failed)
+ count_vm_events(PGMIGRATE_FAIL, nr_failed);
+ trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
+
if (!swapwrite)
current->flags &= ~PF_SWAPWRITE;
- if (rc)
- return rc;
-
- return nr_failed + retry;
+ return rc;
}
-int migrate_huge_pages(struct list_head *from,
- new_page_t get_new_page, unsigned long private, bool offlining,
- bool sync)
+int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
+ unsigned long private, enum migrate_mode mode)
{
- int retry = 1;
- int nr_failed = 0;
- int pass = 0;
- struct page *page;
- struct page *page2;
- int rc;
-
- for (pass = 0; pass < 10 && retry; pass++) {
- retry = 0;
+ int pass, rc;
- list_for_each_entry_safe(page, page2, from, lru) {
+ for (pass = 0; pass < 10; pass++) {
+ rc = unmap_and_move_huge_page(get_new_page, private,
+ hpage, pass > 2, mode);
+ switch (rc) {
+ case -ENOMEM:
+ goto out;
+ case -EAGAIN:
+ /* try again */
cond_resched();
-
- rc = unmap_and_move_huge_page(get_new_page,
- private, page, pass > 2, offlining,
- sync);
-
- switch(rc) {
- case -ENOMEM:
- goto out;
- case -EAGAIN:
- retry++;
- break;
- case 0:
- break;
- default:
- /* Permanent failure */
- nr_failed++;
- break;
- }
+ break;
+ case MIGRATEPAGE_SUCCESS:
+ goto out;
+ default:
+ rc = -EIO;
+ goto out;
}
}
- rc = 0;
out:
- if (rc)
- return rc;
-
- return nr_failed + retry;
+ return rc;
}
#ifdef CONFIG_NUMA
goto set_status;
/* Use PageReserved to check for zero page */
- if (PageReserved(page) || PageKsm(page))
+ if (PageReserved(page))
goto put_and_set;
pp->page = page;
err = 0;
if (!list_empty(&pagelist)) {
err = migrate_pages(&pagelist, new_page_node,
- (unsigned long)pm, 0, true);
+ (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
if (err)
putback_lru_pages(&pagelist);
}
* Migrate an array of page address onto an array of nodes and fill
* the corresponding array of status.
*/
-static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
+static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
unsigned long nr_pages,
const void __user * __user *pages,
const int __user *nodes,
int __user *status, int flags)
{
struct page_to_node *pm;
- nodemask_t task_nodes;
unsigned long chunk_nr_pages;
unsigned long chunk_start;
int err;
- task_nodes = cpuset_mems_allowed(task);
-
err = -ENOMEM;
pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
if (!pm)
if (node < 0 || node >= MAX_NUMNODES)
goto out_pm;
- if (!node_state(node, N_HIGH_MEMORY))
+ if (!node_state(node, N_MEMORY))
goto out_pm;
err = -EACCES;
err = -ENOENT;
/* Use PageReserved to check for zero page */
- if (!page || PageReserved(page) || PageKsm(page))
+ if (!page || PageReserved(page))
goto set_status;
err = page_to_nid(page);
struct task_struct *task;
struct mm_struct *mm;
int err;
+ nodemask_t task_nodes;
/* Check flags */
if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
rcu_read_unlock();
return -ESRCH;
}
- mm = get_task_mm(task);
- rcu_read_unlock();
-
- if (!mm)
- return -EINVAL;
+ get_task_struct(task);
/*
* Check if this process has the right to modify the specified
* capabilities, superuser privileges or the same
* userid as the target process.
*/
- rcu_read_lock();
tcred = __task_cred(task);
- if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
- cred->uid != tcred->suid && cred->uid != tcred->uid &&
+ if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
+ !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) &&
!capable(CAP_SYS_NICE)) {
rcu_read_unlock();
err = -EPERM;
if (err)
goto out;
- if (nodes) {
- err = do_pages_move(mm, task, nr_pages, pages, nodes, status,
- flags);
- } else {
+ task_nodes = cpuset_mems_allowed(task);
+ mm = get_task_mm(task);
+ put_task_struct(task);
+
+ if (!mm)
+ return -EINVAL;
+
+ if (nodes)
+ err = do_pages_move(mm, task_nodes, nr_pages, pages,
+ nodes, status, flags);
+ else
err = do_pages_stat(mm, nr_pages, pages, status);
- }
-out:
mmput(mm);
return err;
+
+out:
+ put_task_struct(task);
+ return err;
}
/*
}
return err;
}
-#endif
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * Returns true if this is a safe migration target node for misplaced NUMA
+ * pages. Currently it only checks the watermarks which crude
+ */
+static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
+ unsigned long nr_migrate_pages)
+{
+ int z;
+ for (z = pgdat->nr_zones - 1; z >= 0; z--) {
+ struct zone *zone = pgdat->node_zones + z;
+
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone->all_unreclaimable)
+ continue;
+
+ /* Avoid waking kswapd by allocating pages_to_migrate pages. */
+ if (!zone_watermark_ok(zone, 0,
+ high_wmark_pages(zone) +
+ nr_migrate_pages,
+ 0, 0))
+ continue;
+ return true;
+ }
+ return false;
+}
+
+static struct page *alloc_misplaced_dst_page(struct page *page,
+ unsigned long data,
+ int **result)
+{
+ int nid = (int) data;
+ struct page *newpage;
+
+ newpage = alloc_pages_exact_node(nid,
+ (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
+ __GFP_NOMEMALLOC | __GFP_NORETRY |
+ __GFP_NOWARN) &
+ ~GFP_IOFS, 0);
+ if (newpage)
+ page_nid_xchg_last(newpage, page_nid_last(page));
+
+ return newpage;
+}
+
+/*
+ * page migration rate limiting control.
+ * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
+ * window of time. Default here says do not migrate more than 1280M per second.
+ * If a node is rate-limited then PTE NUMA updates are also rate-limited. However
+ * as it is faults that reset the window, pte updates will happen unconditionally
+ * if there has not been a fault since @pteupdate_interval_millisecs after the
+ * throttle window closed.
+ */
+static unsigned int migrate_interval_millisecs __read_mostly = 100;
+static unsigned int pteupdate_interval_millisecs __read_mostly = 1000;
+static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);
+
+/* Returns true if NUMA migration is currently rate limited */
+bool migrate_ratelimited(int node)
+{
+ pg_data_t *pgdat = NODE_DATA(node);
+
+ if (time_after(jiffies, pgdat->numabalancing_migrate_next_window +
+ msecs_to_jiffies(pteupdate_interval_millisecs)))
+ return false;
+
+ if (pgdat->numabalancing_migrate_nr_pages < ratelimit_pages)
+ return false;
+
+ return true;
+}
+
+/* Returns true if the node is migrate rate-limited after the update */
+bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages)
+{
+ bool rate_limited = false;
+
+ /*
+ * Rate-limit the amount of data that is being migrated to a node.
+ * Optimal placement is no good if the memory bus is saturated and
+ * all the time is being spent migrating!
+ */
+ spin_lock(&pgdat->numabalancing_migrate_lock);
+ if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
+ pgdat->numabalancing_migrate_nr_pages = 0;
+ pgdat->numabalancing_migrate_next_window = jiffies +
+ msecs_to_jiffies(migrate_interval_millisecs);
+ }
+ if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages)
+ rate_limited = true;
+ else
+ pgdat->numabalancing_migrate_nr_pages += nr_pages;
+ spin_unlock(&pgdat->numabalancing_migrate_lock);
+
+ return rate_limited;
+}
+
+int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
+{
+ int page_lru;
+
+ VM_BUG_ON(compound_order(page) && !PageTransHuge(page));
+
+ /* Avoid migrating to a node that is nearly full */
+ if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page)))
+ return 0;
+
+ if (isolate_lru_page(page))
+ return 0;
+
+ /*
+ * migrate_misplaced_transhuge_page() skips page migration's usual
+ * check on page_count(), so we must do it here, now that the page
+ * has been isolated: a GUP pin, or any other pin, prevents migration.
+ * The expected page count is 3: 1 for page's mapcount and 1 for the
+ * caller's pin and 1 for the reference taken by isolate_lru_page().
+ */
+ if (PageTransHuge(page) && page_count(page) != 3) {
+ putback_lru_page(page);
+ return 0;
+ }
+
+ page_lru = page_is_file_cache(page);
+ mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
+ hpage_nr_pages(page));
+
+ /*
+ * Isolating the page has taken another reference, so the
+ * caller's reference can be safely dropped without the page
+ * disappearing underneath us during migration.
+ */
+ put_page(page);
+ return 1;
+}
+
+/*
+ * Attempt to migrate a misplaced page to the specified destination
+ * node. Caller is expected to have an elevated reference count on
+ * the page that will be dropped by this function before returning.
+ */
+int migrate_misplaced_page(struct page *page, int node)
+{
+ pg_data_t *pgdat = NODE_DATA(node);
+ int isolated;
+ int nr_remaining;
+ LIST_HEAD(migratepages);
+
+ /*
+ * Don't migrate pages that are mapped in multiple processes.
+ * TODO: Handle false sharing detection instead of this hammer
+ */
+ if (page_mapcount(page) != 1)
+ goto out;
+
+ /*
+ * Rate-limit the amount of data that is being migrated to a node.
+ * Optimal placement is no good if the memory bus is saturated and
+ * all the time is being spent migrating!
+ */
+ if (numamigrate_update_ratelimit(pgdat, 1))
+ goto out;
+
+ isolated = numamigrate_isolate_page(pgdat, page);
+ if (!isolated)
+ goto out;
+
+ list_add(&page->lru, &migratepages);
+ nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
+ node, MIGRATE_ASYNC, MR_NUMA_MISPLACED);
+ if (nr_remaining) {
+ putback_lru_pages(&migratepages);
+ isolated = 0;
+ } else
+ count_vm_numa_event(NUMA_PAGE_MIGRATE);
+ BUG_ON(!list_empty(&migratepages));
+ return isolated;
+
+out:
+ put_page(page);
+ return 0;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+/*
+ * Migrates a THP to a given target node. page must be locked and is unlocked
+ * before returning.
+ */
+int migrate_misplaced_transhuge_page(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ pmd_t *pmd, pmd_t entry,
+ unsigned long address,
+ struct page *page, int node)
+{
+ unsigned long haddr = address & HPAGE_PMD_MASK;
+ pg_data_t *pgdat = NODE_DATA(node);
+ int isolated = 0;
+ struct page *new_page = NULL;
+ struct mem_cgroup *memcg = NULL;
+ int page_lru = page_is_file_cache(page);
+
+ /*
+ * Don't migrate pages that are mapped in multiple processes.
+ * TODO: Handle false sharing detection instead of this hammer
+ */
+ if (page_mapcount(page) != 1)
+ goto out_dropref;
+
+ /*
+ * Rate-limit the amount of data that is being migrated to a node.
+ * Optimal placement is no good if the memory bus is saturated and
+ * all the time is being spent migrating!
+ */
+ if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR))
+ goto out_dropref;
+
+ new_page = alloc_pages_node(node,
+ (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+ if (!new_page)
+ goto out_fail;
+
+ page_nid_xchg_last(new_page, page_nid_last(page));
+
+ isolated = numamigrate_isolate_page(pgdat, page);
+ if (!isolated) {
+ put_page(new_page);
+ goto out_fail;
+ }
+
+ /* Prepare a page as a migration target */
+ __set_page_locked(new_page);
+ SetPageSwapBacked(new_page);
+
+ /* anon mapping, we can simply copy page->mapping to the new page: */
+ new_page->mapping = page->mapping;
+ new_page->index = page->index;
+ migrate_page_copy(new_page, page);
+ WARN_ON(PageLRU(new_page));
+
+ /* Recheck the target PMD */
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(*pmd, entry))) {
+ spin_unlock(&mm->page_table_lock);
+
+ /* Reverse changes made by migrate_page_copy() */
+ if (TestClearPageActive(new_page))
+ SetPageActive(page);
+ if (TestClearPageUnevictable(new_page))
+ SetPageUnevictable(page);
+ mlock_migrate_page(page, new_page);
+
+ unlock_page(new_page);
+ put_page(new_page); /* Free it */
+
+ /* Retake the callers reference and putback on LRU */
+ get_page(page);
+ putback_lru_page(page);
+ mod_zone_page_state(page_zone(page),
+ NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
+
+ goto out_unlock;
+ }
+
+ /*
+ * Traditional migration needs to prepare the memcg charge
+ * transaction early to prevent the old page from being
+ * uncharged when installing migration entries. Here we can
+ * save the potential rollback and start the charge transfer
+ * only when migration is already known to end successfully.
+ */
+ mem_cgroup_prepare_migration(page, new_page, &memcg);
+
+ entry = mk_pmd(new_page, vma->vm_page_prot);
+ entry = pmd_mknonnuma(entry);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+ entry = pmd_mkhuge(entry);
+
+ pmdp_clear_flush(vma, haddr, pmd);
+ set_pmd_at(mm, haddr, pmd, entry);
+ page_add_new_anon_rmap(new_page, vma, haddr);
+ update_mmu_cache_pmd(vma, address, &entry);
+ page_remove_rmap(page);
+ /*
+ * Finish the charge transaction under the page table lock to
+ * prevent split_huge_page() from dividing up the charge
+ * before it's fully transferred to the new page.
+ */
+ mem_cgroup_end_migration(memcg, page, new_page, true);
+ spin_unlock(&mm->page_table_lock);
+
+ unlock_page(new_page);
+ unlock_page(page);
+ put_page(page); /* Drop the rmap reference */
+ put_page(page); /* Drop the LRU isolation reference */
+
+ count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
+ count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
+
+ mod_zone_page_state(page_zone(page),
+ NR_ISOLATED_ANON + page_lru,
+ -HPAGE_PMD_NR);
+ return isolated;
+
+out_fail:
+ count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
+out_dropref:
+ entry = pmd_mknonnuma(entry);
+ set_pmd_at(mm, haddr, pmd, entry);
+ update_mmu_cache_pmd(vma, address, &entry);
+
+out_unlock:
+ unlock_page(page);
+ put_page(page);
+ return 0;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+#endif /* CONFIG_NUMA */