---

yaml
---
r: 28951
b: refs/heads/master
c: 742755a
h: refs/heads/master
i:
  28949: d4503e8
  28947: 4503504
  28943: 654a55d
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 95a402c3847cc16f4ba03013cd01404fa0f14c2e
+refs/heads/master: 742755a1d8ce2b548428f7aacf1758b4bba50080

trunk/Documentation/vm/page_migration

@@ -26,8 +26,13 @@ a process are located. See also the numa_maps manpage in the numactl package.
 Manual migration is useful if for example the scheduler has relocated
 a process to a processor on a distant node. A batch scheduler or an
 administrator may detect the situation and move the pages of the process
-nearer to the new processor. At some point in the future we may have
-some mechanism in the scheduler that will automatically move the pages.
+nearer to the new processor. The kernel itself does only provide
+manual page migration support. Automatic page migration may be implemented
+through user space processes that move pages. A special function call
+"move_pages" allows the moving of individual pages within a process.
+A NUMA profiler may f.e. obtain a log showing frequent off node
+accesses and may use the result to move pages to more advantageous
+locations.
 
 Larger installations usually partition the system using cpusets into
 sections of nodes. Paul Jackson has equipped cpusets with the ability to
@@ -62,22 +67,14 @@ A. In kernel use of migrate_pages()
    It also prevents the swapper or other scans to encounter
    the page.
 
-2. Generate a list of newly allocates pages. These pages will contain the
-   contents of the pages from the first list after page migration is
-   complete.
+2. We need to have a function of type new_page_t that can be
+   passed to migrate_pages(). This function should figure out
+   how to allocate the correct new page given the old page.
 
 3. The migrate_pages() function is called which attempts
-   to do the migration. It returns the moved pages in the
-   list specified as the third parameter and the failed
-   migrations in the fourth parameter. When the function
-   returns the first list will contain the pages that could still be retried.
-
-4. The leftover pages of various types are returned
-   to the LRU using putback_to_lru_pages() or otherwise
-   disposed of. The pages will still have the refcount as
-   increased by isolate_lru_pages() if putback_to_lru_pages() is not
-   used! The kernel may want to handle the various cases of failures in
-   different ways.
+   to do the migration. It will call the function to allocate
+   the new page for each page that is considered for
+   moving.
 
 B. How migrate_pages() works
 ----------------------------

trunk/arch/ia64/kernel/entry.S

@@ -1584,7 +1584,7 @@ sys_call_table:
 	data8 sys_keyctl
 	data8 sys_ioprio_set
 	data8 sys_ioprio_get			// 1275
-	data8 sys_ni_syscall
+	data8 sys_move_pages
 	data8 sys_inotify_init
 	data8 sys_inotify_add_watch
 	data8 sys_inotify_rm_watch

trunk/include/asm-ia64/unistd.h

@@ -265,7 +265,7 @@
 #define __NR_keyctl			1273
 #define __NR_ioprio_set			1274
 #define __NR_ioprio_get			1275
-/* 1276 is available for reuse (was briefly sys_set_zone_reclaim) */
+#define __NR_move_pages			1276
 #define __NR_inotify_init		1277
 #define __NR_inotify_add_watch		1278
 #define __NR_inotify_rm_watch		1279

trunk/include/linux/migrate.h

@@ -3,7 +3,7 @@
 
 #include <linux/mm.h>
 
-typedef struct page *new_page_t(struct page *, unsigned long private);
+typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
 #ifdef CONFIG_MIGRATION
 extern int isolate_lru_page(struct page *p, struct list_head *pagelist);

trunk/include/linux/syscalls.h

@@ -516,6 +516,11 @@ asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
 asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 				const unsigned long __user *from,
 				const unsigned long __user *to);
+asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
+				const void __user * __user *pages,
+				const int __user *nodes,
+				int __user *status,
+				int flags);
 asmlinkage long sys_mbind(unsigned long start, unsigned long len,
 				unsigned long mode,
 				unsigned long __user *nmask,

trunk/kernel/sys_ni.c

@@ -87,6 +87,7 @@ cond_syscall(sys_inotify_init);
 cond_syscall(sys_inotify_add_watch);
 cond_syscall(sys_inotify_rm_watch);
 cond_syscall(sys_migrate_pages);
+cond_syscall(sys_move_pages);
 cond_syscall(sys_chown16);
 cond_syscall(sys_fchown16);
 cond_syscall(sys_getegid16);

trunk/mm/mempolicy.c

@@ -588,7 +588,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 		isolate_lru_page(page, pagelist);
 }
 
-static struct page *new_node_page(struct page *page, unsigned long node)
+static struct page *new_node_page(struct page *page, unsigned long node, int **x)
 {
 	return alloc_pages_node(node, GFP_HIGHUSER, 0);
 }
@@ -698,7 +698,7 @@ int do_migrate_pages(struct mm_struct *mm,
 
 }
 
-static struct page *new_vma_page(struct page *page, unsigned long private)
+static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
 {
 	struct vm_area_struct *vma = (struct vm_area_struct *)private;