[PATCH/RFC 5/8] numa - Migrate-on-Fault - migrate misplaced anon pages

[Lee Schermerhorn <lee.schermerhorn@hp.com>]

Migrate-on-fault  - handle misplaced anon pages

This patch simply hooks the anon page fault handler [do_swap_page()]
to check for and migrate misplaced pages if enabled and page won't
be "COWed".

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>

 mm/memory.c   |   27 +++++++++++++++++++++++++++
 mm/shmem.c    |   10 ++++++++++
 mm/swapfile.c |    9 +++++++++
 3 files changed, 46 insertions(+)

Index: linux-2.6.36-mmotm-101103-1217/mm/memory.c
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/mm/memory.c
+++ linux-2.6.36-mmotm-101103-1217/mm/memory.c
@@ -57,6 +57,7 @@
 #include <linux/swapops.h>
 #include <linux/elf.h>
 #include <linux/gfp.h>
+#include <linux/mempolicy.h>	/* check_migrate_misplaced_page() */
 
 #include <asm/io.h>
 #include <asm/pgalloc.h>
@@ -2632,6 +2633,7 @@ static int do_swap_page(struct mm_struct
 	struct mem_cgroup *ptr = NULL;
 	int exclusive = 0;
 	int ret = 0;
+	int can_reuse;
 
 	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
 		goto out;
@@ -2716,6 +2718,31 @@ static int do_swap_page(struct mm_struct
 	}
 
 	/*
+	 * No sense in migrating a page that will be "COWed" as the new
+	 * new page will be allocated according to effective mempolicy.
+	 */
+	can_reuse = (flags & FAULT_FLAG_WRITE) && reuse_swap_page(page);
+	if (can_reuse && migrate_on_fault_enabled(current)) {
+		if (!PageSwapCache(page)) {
+			/*
+			 *  migrate-on-fault has occurred - retry access
+			 */
+			mem_cgroup_cancel_charge_swapin(ptr);
+			goto out_page;
+		}
+
+		/*
+		 * check for misplacement and migrate, if necessary/possible,
+		 * here and now.  Note that if we're racing with another thread,
+		 * we may end up discarding the migrated page after locking
+		 * the page table and checking the pte below.  However, we
+		 * don't want to hold the page table locked over migration, so
+		 * we'll live with that [unlikely, one hopes] possibility.
+		 */
+		page = check_migrate_misplaced_page(page, vma, address);
+	}
+
+	/*
 	 * Back out if somebody else already faulted in this pte.
 	 */
 	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
Index: linux-2.6.36-mmotm-101103-1217/mm/swapfile.c
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/mm/swapfile.c
+++ linux-2.6.36-mmotm-101103-1217/mm/swapfile.c
@@ -1143,6 +1143,7 @@ static int try_to_unuse(unsigned int typ
 		 */
 		swap_map = &si->swap_map[i];
 		entry = swp_entry(type, i);
+	again:
 		pol = get_vma_policy(current, NULL, 0);
 		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
 							 pol, i);
@@ -1179,6 +1180,14 @@ static int try_to_unuse(unsigned int typ
 		wait_on_page_locked(page);
 		wait_on_page_writeback(page);
 		lock_page(page);
+		if (!PageSwapCache(page)) {
+			/*
+			 * Lazy page migration has occurred
+			 */
+			unlock_page(page);
+			page_cache_release(page);
+			goto again;
+		}
 		wait_on_page_writeback(page);
 
 		/*
Index: linux-2.6.36-mmotm-101103-1217/mm/shmem.c
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/mm/shmem.c
+++ linux-2.6.36-mmotm-101103-1217/mm/shmem.c
@@ -1304,6 +1304,16 @@ repeat:
 			page_cache_release(swappage);
 			goto repeat;
 		}
+		if (!PageSwapCache(swappage)) {
+			/*
+			 * Lazy page migration has occurred
+			 */
+			shmem_swp_unmap(entry);
+			spin_unlock(&info->lock);
+			unlock_page(swappage);
+			page_cache_release(swappage);
+			goto repeat;
+		}
 		if (PageWriteback(swappage)) {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);