Merge branch 'akpm' (incoming from Andrew)

Merge second patch-bomb from Andrew Morton:
 - the rest of MM
 - zram updates
 - zswap updates
 - exit
 - procfs
 - exec
 - wait
 - crash dump
 - lib/idr
 - rapidio
 - adfs, affs, bfs, ufs
 - cris
 - Kconfig things
 - initramfs
 - small amount of IPC material
 - percpu enhancements
 - early ioremap support
 - various other misc things

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (156 commits)
  MAINTAINERS: update Intel C600 SAS driver maintainers
  fs/ufs: remove unused ufs_super_block_third pointer
  fs/ufs: remove unused ufs_super_block_second pointer
  fs/ufs: remove unused ufs_super_block_first pointer
  fs/ufs/super.c: add __init to init_inodecache()
  doc/kernel-parameters.txt: add early_ioremap_debug
  arm64: add early_ioremap support
  arm64: initialize pgprot info earlier in boot
  x86: use generic early_ioremap
  mm: create generic early_ioremap() support
  x86/mm: sparse warning fix for early_memremap
  lglock: map to spinlock when !CONFIG_SMP
  percpu: add preemption checks to __this_cpu ops
  vmstat: use raw_cpu_ops to avoid false positives on preemption checks
  slub: use raw_cpu_inc for incrementing statistics
  net: replace __this_cpu_inc in route.c with raw_cpu_inc
  modules: use raw_cpu_write for initialization of per cpu refcount.
  mm: use raw_cpu ops for determining current NUMA node
  percpu: add raw_cpu_ops
  slub: fix leak of 'name' in sysfs_slab_add
  ...

1 files changed, 49 insertions, 7 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 769a67a15803..c43d557941f8 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -36,6 +36,34 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 }
 #endif
 
+/*
+ * For a prot_numa update we only hold mmap_sem for read so there is a
+ * potential race with faulting where a pmd was temporarily none. This
+ * function checks for a transhuge pmd under the appropriate lock. It
+ * returns a pte if it was successfully locked or NULL if it raced with
+ * a transhuge insertion.
+ */
+static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, int prot_numa, spinlock_t **ptl)
+{
+	pte_t *pte;
+	spinlock_t *pmdl;
+
+	/* !prot_numa is protected by mmap_sem held for write */
+	if (!prot_numa)
+		return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+
+	pmdl = pmd_lock(vma->vm_mm, pmd);
+	if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
+		spin_unlock(pmdl);
+		return NULL;
+	}
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+	spin_unlock(pmdl);
+	return pte;
+}
+
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable, int prot_numa)
@@ -45,7 +73,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	spinlock_t *ptl;
 	unsigned long pages = 0;
 
-	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+	if (!pte)
+		return 0;
+
 	arch_enter_lazy_mmu_mode();
 	do {
 		oldpte = *pte;
@@ -109,15 +140,26 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
 {
 	pmd_t *pmd;
+	struct mm_struct *mm = vma->vm_mm;
 	unsigned long next;
 	unsigned long pages = 0;
 	unsigned long nr_huge_updates = 0;
+	unsigned long mni_start = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
 		unsigned long this_pages;
 
 		next = pmd_addr_end(addr, end);
+		if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd))
+			continue;
+
+		/* invoke the mmu notifier if the pmd is populated */
+		if (!mni_start) {
+			mni_start = addr;
+			mmu_notifier_invalidate_range_start(mm, mni_start, end);
+		}
+
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma, addr, pmd);
@@ -130,18 +172,21 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 						pages += HPAGE_PMD_NR;
 						nr_huge_updates++;
 					}
+
+					/* huge pmd was handled */
 					continue;
 				}
 			}
-			/* fall through */
+			/* fall through, the trans huge pmd just split */
 		}
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
 		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
 				 dirty_accountable, prot_numa);
 		pages += this_pages;
 	} while (pmd++, addr = next, addr != end);
 
+	if (mni_start)
+		mmu_notifier_invalidate_range_end(mm, mni_start, end);
+
 	if (nr_huge_updates)
 		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
@@ -201,15 +246,12 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
 		       int dirty_accountable, int prot_numa)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	unsigned long pages;
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
 		pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
-	mmu_notifier_invalidate_range_end(mm, start, end);
 
 	return pages;
 }