Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull NUMA balancing memory corruption fixes from Ingo Molnar:
 "So these fixes are definitely not something I'd like to sit on, but as
  I said to Mel at the KS the timing is quite tight, with Linus planning
  v3.12-final within a week.

  Fedora-19 is affected:

   comet:~> grep NUMA_BALANCING /boot/config-3.11.3-201.fc19.x86_64

   CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y
   CONFIG_NUMA_BALANCING_DEFAULT_ENABLED=y
   CONFIG_NUMA_BALANCING=y

  AFAICS Ubuntu will be affected as well, once it updates the kernel:

   hubble:~> grep NUMA_BALANCING /boot/config-3.8.0-32-generic

   CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y
   CONFIG_NUMA_BALANCING_DEFAULT_ENABLED=y
   CONFIG_NUMA_BALANCING=y

  These 6 commits are a minimalized set of cherry-picks needed to fix
  the memory corruption bugs.  All commits are fixes, except "mm: numa:
  Sanitize task_numa_fault() callsites" which is a cleanup that made two
  followup fixes simpler.

  I've done targeted testing with just this SHA1 to try to make sure
  there are no cherry-picking artifacts.  The original non-cherry-picked
  set of fixes were exposed to linux-next for a couple of weeks"

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  mm: Account for a THP NUMA hinting update as one PTE update
  mm: Close races between THP migration and PMD numa clearing
  mm: numa: Sanitize task_numa_fault() callsites
  mm: Prevent parallel splits during THP migration
  mm: Wait for THP migrations to complete during NUMA hinting faults
  mm: numa: Do not account for a hinting fault if we raced

1 files changed, 21 insertions, 32 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 1311f26497e6..d176154c243f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3521,12 +3521,12 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-				unsigned long addr, int current_nid)
+				unsigned long addr, int page_nid)
 {
 	get_page(page);
 
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == numa_node_id())
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
 	return mpol_misplaced(page, vma, addr);
@@ -3537,7 +3537,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid = -1;
+	int page_nid = -1;
 	int target_nid;
 	bool migrated = false;
 
@@ -3567,15 +3567,10 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return 0;
 	}
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	page_nid = page_to_nid(page);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
-		/*
-		 * Account for the fault against the current node if it not
-		 * being replaced regardless of where the page is located.
-		 */
-		current_nid = numa_node_id();
 		put_page(page);
 		goto out;
 	}
@@ -3583,11 +3578,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Migrate to the requested node */
 	migrated = migrate_misplaced_page(page, target_nid);
 	if (migrated)
-		current_nid = target_nid;
+		page_nid = target_nid;
 
 out:
-	if (current_nid != -1)
-		task_numa_fault(current_nid, 1, migrated);
+	if (page_nid != -1)
+		task_numa_fault(page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3602,7 +3597,6 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int local_nid = numa_node_id();
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3625,9 +3619,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
 		pte_t pteval = *pte;
 		struct page *page;
-		int curr_nid = local_nid;
+		int page_nid = -1;
 		int target_nid;
-		bool migrated;
+		bool migrated = false;
+
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3649,25 +3644,19 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(page_mapcount(page) != 1))
 			continue;
 
-		/*
-		 * Note that the NUMA fault is later accounted to either
-		 * the node that is currently running or where the page is
-		 * migrated to.
-		 */
-		curr_nid = local_nid;
-		target_nid = numa_migrate_prep(page, vma, addr,
-					       page_to_nid(page));
-		if (target_nid == -1) {
+		page_nid = page_to_nid(page);
+		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+		pte_unmap_unlock(pte, ptl);
+		if (target_nid != -1) {
+			migrated = migrate_misplaced_page(page, target_nid);
+			if (migrated)
+				page_nid = target_nid;
+		} else {
 			put_page(page);
-			continue;
 		}
 
-		/* Migrate to the requested node */
-		pte_unmap_unlock(pte, ptl);
-		migrated = migrate_misplaced_page(page, target_nid);
-		if (migrated)
-			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1, migrated);
+		if (page_nid != -1)
+			task_numa_fault(page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}