Merge branch 'linux-3.0.y' into cm.ics

9 files changed, 35 insertions, 33 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 01d5a4b3..9686c4e 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -768,14 +768,13 @@ void * __init alloc_bootmem_section(unsigned long size,
 				    unsigned long section_nr)
 {
 	bootmem_data_t *bdata;
-	unsigned long pfn, goal, limit;
+	unsigned long pfn, goal;
 
 	pfn = section_nr_to_pfn(section_nr);
 	goal = pfn << PAGE_SHIFT;
-	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
 	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
 
-	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit);
+	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, 0);
 }
 #endif
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 45059db..283068f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5290,6 +5290,8 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	spinlock_t *ptl;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
@@ -5451,6 +5453,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	spinlock_t *ptl;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 retry:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
diff --git a/mm/memory.c b/mm/memory.c
index 95a7799..d49b58a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1228,16 +1228,24 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 	do {
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*pmd)) {
-			if (next-addr != HPAGE_PMD_SIZE) {
+			if (next - addr != HPAGE_PMD_SIZE) {
 				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
 				split_huge_page_pmd(vma->vm_mm, pmd);
 			} else if (zap_huge_pmd(tlb, vma, pmd))
-				continue;
+				goto next;
 			/* fall through */
 		}
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
+		/*
+		 * Here there can be other concurrent MADV_DONTNEED or
+		 * trans huge page faults running, and if the pmd is
+		 * none or trans huge it can change under us. This is
+		 * because MADV_DONTNEED holds the mmap_sem in read
+		 * mode.
+		 */
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+			goto next;
 		next = zap_pte_range(tlb, vma, pmd, addr, next, details);
+next:
 		cond_resched();
 	} while (pmd++, addr = next, addr != end);
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e7fb9d2..a85171d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -511,7 +511,7 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	do {
 		next = pmd_addr_end(addr, end);
 		split_huge_page_pmd(vma->vm_mm, pmd);
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			continue;
 		if (check_pte_range(vma, pmd, addr, next, nodes,
 				    flags, private))
diff --git a/mm/mincore.c b/mm/mincore.c
index a4e6b9d..117ff54 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -161,7 +161,7 @@ static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 			}
 			/* fall through */
 		}
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			mincore_unmapped_range(vma, addr, next, vec);
 		else
 			mincore_pte_range(vma, pmd, addr, next, vec);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index c3450d5..87eac0e 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -59,7 +59,7 @@ again:
 			continue;
 
 		split_huge_page_pmd(walk->mm, pmd);
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			goto again;
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
diff --git a/mm/slub.c b/mm/slub.c
index 0d0901e..10ab233 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3439,13 +3439,14 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		if (kmem_cache_open(s, n,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
+			up_write(&slub_lock);
 			if (sysfs_slab_add(s)) {
+				down_write(&slub_lock);
 				list_del(&s->list);
 				kfree(n);
 				kfree(s);
 				goto err;
 			}
-			up_write(&slub_lock);
 			return s;
 		}
 		kfree(n);
diff --git a/mm/sparse.c b/mm/sparse.c
index aa64b12..4cd05e5 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -353,29 +353,21 @@ static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
 
 	usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
 								 usemap_count);
-	if (usemap) {
-		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
-			if (!present_section_nr(pnum))
-				continue;
-			usemap_map[pnum] = usemap;
-			usemap += size;
+	if (!usemap) {
+		usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
+		if (!usemap) {
+			printk(KERN_WARNING "%s: allocation failed\n", __func__);
+			return;
 		}
-		return;
 	}
 
-	usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
-	if (usemap) {
-		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
-			if (!present_section_nr(pnum))
-				continue;
-			usemap_map[pnum] = usemap;
-			usemap += size;
-			check_usemap_section_nr(nodeid, usemap_map[pnum]);
-		}
-		return;
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		if (!present_section_nr(pnum))
+			continue;
+		usemap_map[pnum] = usemap;
+		usemap += size;
+		check_usemap_section_nr(nodeid, usemap_map[pnum]);
 	}
-
-	printk(KERN_WARNING "%s: allocation failed\n", __func__);
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/mm/swapfile.c b/mm/swapfile.c
index ff8dc1a..c8f4338 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -932,9 +932,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (unlikely(pmd_trans_huge(*pmd)))
-			continue;
-		if (pmd_none_or_clear_bad(pmd))
+		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
 			continue;
 		ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
 		if (ret)