aboutsummaryrefslogtreecommitdiff
path: root/mm/migrate.c
diff options
context:
space:
mode:
authorHugh Dickins <hugh.dickins@tiscali.co.uk>2009-12-14 17:59:33 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-12-15 08:53:20 -0800
commit62b61f611eb5e20f7e9f8619bfd03bdfe8af6348 (patch)
tree9f06fff7eb6530fbe90b4d998b91071133f6af25 /mm/migrate.c
parente9995ef978a7d5296fe04a9a2c5ca6e66d8bb4e5 (diff)
ksm: memory hotremove migration only
The previous patch enables page migration of ksm pages, but that soon gets into trouble: not surprising, since we're using the ksm page lock to lock operations on its stable_node, but page migration switches the page whose lock is to be used for that. Another layer of locking would fix it, but do we need that yet? Do we actually need page migration of ksm pages? Yes, memory hotremove needs to offline sections of memory: and since we stopped allocating ksm pages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE candidates for migration. But KSM is currently unconscious of NUMA issues, happily merging pages from different NUMA nodes: at present the rule must be, not to use MADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of ksm pages does not make sense yet. So, to complete support for ksm swapping we need to make hotremove safe. ksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and release it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages are freed before migration reaches them, stable_nodes may be left still pointing to struct pages which have been removed from the system: the stable_node needs to identify a page by pfn rather than page pointer, then it can safely prune them when MEM_OFFLINE. And make NUMA migration skip PageKsm pages where it skips PageReserved. But it's only when we reach unmap_and_move() that the page lock is taken and we can be sure that raised pagecount has prevented a PageAnon from being upgraded: so add offlining arg to migrate_pages(), to migrate ksm page when offlining (has sufficient locking) but reject it otherwise. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Izik Eidus <ieidus@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Chris Wright <chrisw@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/migrate.c')
-rw-r--r--mm/migrate.c27
1 files changed, 21 insertions, 6 deletions
diff --git a/mm/migrate.c b/mm/migrate.c
index 0b714747c02..2a0ea3ef509 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -543,7 +543,7 @@ static int move_to_new_page(struct page *newpage, struct page *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)
+ struct page *page, int force, int offlining)
{
int rc = 0;
int *result = NULL;
@@ -569,6 +569,20 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
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, &mem);
if (charge == -ENOMEM) {
@@ -685,7 +699,7 @@ move_newpage:
* Return: Number of pages not migrated or error code.
*/
int migrate_pages(struct list_head *from,
- new_page_t get_new_page, unsigned long private)
+ new_page_t get_new_page, unsigned long private, int offlining)
{
int retry = 1;
int nr_failed = 0;
@@ -705,7 +719,7 @@ int migrate_pages(struct list_head *from,
cond_resched();
rc = unmap_and_move(get_new_page, private,
- page, pass > 2);
+ page, pass > 2, offlining);
switch(rc) {
case -ENOMEM:
@@ -801,7 +815,8 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
if (!page)
goto set_status;
- if (PageReserved(page)) /* Check for zero page */
+ /* Use PageReserved to check for zero page */
+ if (PageReserved(page) || PageKsm(page))
goto put_and_set;
pp->page = page;
@@ -838,7 +853,7 @@ set_status:
err = 0;
if (!list_empty(&pagelist))
err = migrate_pages(&pagelist, new_page_node,
- (unsigned long)pm);
+ (unsigned long)pm, 0);
up_read(&mm->mmap_sem);
return err;
@@ -959,7 +974,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
err = -ENOENT;
/* Use PageReserved to check for zero page */
- if (!page || PageReserved(page))
+ if (!page || PageReserved(page) || PageKsm(page))
goto set_status;
err = page_to_nid(page);