Merge tag 'v3.5-rc6' into x86/mce

Merge Linux 3.5-rc6 before merging more code.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 104 insertions, 44 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index deff1b64a08c..14d260fa0d17 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/ksm.h>
 #include <linux/fs.h>
+#include <linux/file.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -204,14 +205,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 {
 	loff_t offset;
 	int error;
+	struct file *f;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
 	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
 		return -EINVAL;
 
-	if (!vma->vm_file || !vma->vm_file->f_mapping
-		|| !vma->vm_file->f_mapping->host) {
+	f = vma->vm_file;
+
+	if (!f || !f->f_mapping || !f->f_mapping->host) {
 			return -EINVAL;
 	}
 
@@ -221,11 +224,18 @@ static long madvise_remove(struct vm_area_struct *vma,
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* filesystem's fallocate may need to take i_mutex */
+	/*
+	 * Filesystem's fallocate may need to take i_mutex.  We need to
+	 * explicitly grab a reference because the vma (and hence the
+	 * vma's reference to the file) can go away as soon as we drop
+	 * mmap_sem.
+	 */
+	get_file(f);
 	up_read(&current->mm->mmap_sem);
-	error = do_fallocate(vma->vm_file,
+	error = do_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
+	fput(f);
 	down_read(&current->mm->mmap_sem);
 	return error;
 }
diff --git a/mm/memblock.c b/mm/memblock.c
index 952123eba433..d4382095f8bd 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -184,7 +184,24 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 	}
 }
 
-static int __init_memblock memblock_double_array(struct memblock_type *type)
+/**
+ * memblock_double_array - double the size of the memblock regions array
+ * @type: memblock type of the regions array being doubled
+ * @new_area_start: starting address of memory range to avoid overlap with
+ * @new_area_size: size of memory range to avoid overlap with
+ *
+ * Double the size of the @type regions array. If memblock is being used to
+ * allocate memory for a new reserved regions array and there is a previously
+ * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
+ * waiting to be reserved, ensure the memory used by the new array does
+ * not overlap.
+ *
+ * RETURNS:
+ * 0 on success, -1 on failure.
+ */
+static int __init_memblock memblock_double_array(struct memblock_type *type,
+						phys_addr_t new_area_start,
+						phys_addr_t new_area_size)
 {
 	struct memblock_region *new_array, *old_array;
 	phys_addr_t old_size, new_size, addr;
@@ -222,7 +239,18 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 		new_array = kmalloc(new_size, GFP_KERNEL);
 		addr = new_array ? __pa(new_array) : 0;
 	} else {
-		addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
+		/* only exclude range when trying to double reserved.regions */
+		if (type != &memblock.reserved)
+			new_area_start = new_area_size = 0;
+
+		addr = memblock_find_in_range(new_area_start + new_area_size,
+						memblock.current_limit,
+						new_size, sizeof(phys_addr_t));
+		if (!addr && new_area_size)
+			addr = memblock_find_in_range(0,
+					min(new_area_start, memblock.current_limit),
+					new_size, sizeof(phys_addr_t));
+
 		new_array = addr ? __va(addr) : 0;
 	}
 	if (!addr) {
@@ -399,7 +427,7 @@ repeat:
 	 */
 	if (!insert) {
 		while (type->cnt + nr_new > type->max)
-			if (memblock_double_array(type) < 0)
+			if (memblock_double_array(type, obase, size) < 0)
 				return -ENOMEM;
 		insert = true;
 		goto repeat;
@@ -450,7 +478,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 
 	/* we'll create at most two more regions */
 	while (type->cnt + 2 > type->max)
-		if (memblock_double_array(type) < 0)
+		if (memblock_double_array(type, base, size) < 0)
 			return -ENOMEM;
 
 	for (i = 0; i < type->cnt; i++) {
@@ -540,9 +568,9 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
  * __next_free_mem_range - next function for for_each_free_mem_range()
  * @idx: pointer to u64 loop variable
  * @nid: nid: node selector, %MAX_NUMNODES for all nodes
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- * @p_nid: ptr to int for nid of the range, can be %NULL
+ * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @out_nid: ptr to int for nid of the range, can be %NULL
  *
  * Find the first free area from *@idx which matches @nid, fill the out
  * parameters, and update *@idx for the next iteration.  The lower 32bit of
@@ -616,9 +644,9 @@ void __init_memblock __next_free_mem_range(u64 *idx, int nid,
  * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse()
  * @idx: pointer to u64 loop variable
  * @nid: nid: node selector, %MAX_NUMNODES for all nodes
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- * @p_nid: ptr to int for nid of the range, can be %NULL
+ * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ * @out_nid: ptr to int for nid of the range, can be %NULL
  *
  * Reverse of __next_free_mem_range().
  */
@@ -867,6 +895,16 @@ int __init_memblock memblock_is_memory(phys_addr_t addr)
 	return memblock_search(&memblock.memory, addr) != -1;
 }
 
+/**
+ * memblock_is_region_memory - check if a region is a subset of memory
+ * @base: base of region to check
+ * @size: size of region to check
+ *
+ * Check if the region [@base, @base+@size) is a subset of a memory block.
+ *
+ * RETURNS:
+ * 0 if false, non-zero if true
+ */
 int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
 {
 	int idx = memblock_search(&memblock.memory, base);
@@ -879,6 +917,16 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size
 		 memblock.memory.regions[idx].size) >= end;
 }
 
+/**
+ * memblock_is_region_reserved - check if a region intersects reserved memory
+ * @base: base of region to check
+ * @size: size of region to check
+ *
+ * Check if the region [@base, @base+@size) intersects a reserved memory block.
+ *
+ * RETURNS:
+ * 0 if false, non-zero if true
+ */
 int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
 {
 	memblock_cap_size(base, &size);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ac35bccadb7b..f72b5e52451a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1148,7 +1148,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 {
 	if (root_memcg == memcg)
 		return true;
-	if (!root_memcg->use_hierarchy)
+	if (!root_memcg->use_hierarchy || !memcg)
 		return false;
 	return css_is_ancestor(&memcg->css, &root_memcg->css);
 }
@@ -1234,7 +1234,7 @@ int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec)
 
 /**
  * mem_cgroup_margin - calculate chargeable space of a memory cgroup
- * @mem: the memory cgroup
+ * @memcg: the memory cgroup
  *
  * Returns the maximum amount of memory @mem can be charged with, in
  * pages.
@@ -1508,7 +1508,7 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
 
 /**
  * test_mem_cgroup_node_reclaimable
- * @mem: the target memcg
+ * @memcg: the target memcg
  * @nid: the node ID to be checked.
  * @noswap : specify true here if the user wants flle only information.
  *
diff --git a/mm/memory.c b/mm/memory.c
index 1b7dc662bf9f..2466d1250231 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1225,7 +1225,15 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 		next = pmd_addr_end(addr, end);
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE) {
-				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
+#ifdef CONFIG_DEBUG_VM
+				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
+					pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
+						__func__, addr, end,
+						vma->vm_start,
+						vma->vm_end);
+					BUG();
+				}
+#endif
 				split_huge_page_pmd(vma->vm_mm, pmd);
 			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
@@ -1366,7 +1374,7 @@ void unmap_vmas(struct mmu_gather *tlb,
 /**
  * zap_page_range - remove user pages in a given range
  * @vma: vm_area_struct holding the applicable pages
- * @address: starting address of pages to zap
+ * @start: starting address of pages to zap
  * @size: number of bytes to zap
  * @details: details of nonlinear truncation or shared cache invalidation
  *
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f15c1b24ca18..1d771e4200d2 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1177,7 +1177,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (!list_empty(&pagelist)) {
 			nr_failed = migrate_pages(&pagelist, new_vma_page,
 						(unsigned long)vma,
-						false, true);
+						false, MIGRATE_SYNC);
 			if (nr_failed)
 				putback_lru_pages(&pagelist);
 		}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ed0e19677360..ac300c99baf6 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -183,7 +183,8 @@ static bool oom_unkillable_task(struct task_struct *p,
 unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 			  const nodemask_t *nodemask, unsigned long totalpages)
 {
-	unsigned long points;
+	long points;
+	long adj;
 
 	if (oom_unkillable_task(p, memcg, nodemask))
 		return 0;
@@ -192,7 +193,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	if (!p)
 		return 0;
 
-	if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+	adj = p->signal->oom_score_adj;
+	if (adj == OOM_SCORE_ADJ_MIN) {
 		task_unlock(p);
 		return 0;
 	}
@@ -210,20 +212,17 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * implementation used by LSMs.
 	 */
 	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		points -= 30 * totalpages / 1000;
+		adj -= 30;
 
-	/*
-	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
-	 * either completely disable oom killing or always prefer a certain
-	 * task.
-	 */
-	points += p->signal->oom_score_adj * totalpages / 1000;
+	/* Normalize to oom_score_adj units */
+	adj *= totalpages / 1000;
+	points += adj;
 
 	/*
 	 * Never return 0 for an eligible task regardless of the root bonus and
 	 * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
 	 */
-	return points ? points : 1;
+	return points > 0 ? points : 1;
 }
 
 /*
@@ -366,7 +365,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 
 /**
  * dump_tasks - dump current memory state of all system tasks
- * @mem: current's memory controller, if constrained
+ * @memcg: current's memory controller, if constrained
  * @nodemask: nodemask passed to page allocator for mempolicy ooms
  *
  * Dumps the current memory state of all eligible tasks.  Tasks not in the same
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 1ccbd714059c..eb750f851395 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -392,7 +392,7 @@ static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
 
 /**
  * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
- * @end: swap entry to be cmpxchged
+ * @ent: swap entry to be cmpxchged
  * @old: old id
  * @new: new id
  *
@@ -422,7 +422,7 @@ unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
 /**
  * swap_cgroup_record - record mem_cgroup for this swp_entry.
  * @ent: swap entry to be recorded into
- * @mem: mem_cgroup to be recorded
+ * @id: mem_cgroup to be recorded
  *
  * Returns old value at success, 0 at failure.
  * (Of course, old value can be 0.)
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index aa9701e12714..6c118d012bb5 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -162,7 +162,6 @@ static int walk_hugetlb_range(struct vm_area_struct *vma,
 
 /**
  * walk_page_range - walk a memory map's page tables with a callback
- * @mm: memory map to walk
  * @addr: starting address
  * @end: ending address
  * @walk: set of callbacks to invoke for each level of the tree
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 405d331804c3..3707c71ae4cd 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -360,7 +360,6 @@ err_free:
  * @chunk: chunk to depopulate
  * @off: offset to the area to depopulate
  * @size: size of the area to depopulate in bytes
- * @flush: whether to flush cache and tlb or not
  *
  * For each cpu, depopulate and unmap pages [@page_start,@page_end)
  * from @chunk.  If @flush is true, vcache is flushed before unmapping
diff --git a/mm/shmem.c b/mm/shmem.c
index a15a466d0d1d..4ce02e0673db 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1594,6 +1594,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &page_cache_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -1682,7 +1683,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 
 	if (error > 0) {
 		*ppos += error;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index de5bc51c4a66..71373d03fcee 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1916,24 +1916,20 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 
 	/*
 	 * Find out how many pages are allowed for a single swap
-	 * device. There are three limiting factors: 1) the number
+	 * device. There are two limiting factors: 1) the number
 	 * of bits for the swap offset in the swp_entry_t type, and
 	 * 2) the number of bits in the swap pte as defined by the
-	 * the different architectures, and 3) the number of free bits
-	 * in an exceptional radix_tree entry. In order to find the
+	 * different architectures. In order to find the
 	 * largest possible bit mask, a swap entry with swap type 0
 	 * and swap offset ~0UL is created, encoded to a swap pte,
 	 * decoded to a swp_entry_t again, and finally the swap
 	 * offset is extracted. This will mask all the bits from
 	 * the initial ~0UL mask that can't be encoded in either
 	 * the swp_entry_t or the architecture definition of a
-	 * swap pte.  Then the same is done for a radix_tree entry.
+	 * swap pte.
 	 */
 	maxpages = swp_offset(pte_to_swp_entry(
-			swp_entry_to_pte(swp_entry(0, ~0UL))));
-	maxpages = swp_offset(radix_to_swp_entry(
-			swp_to_radix_entry(swp_entry(0, maxpages)))) + 1;
-
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
 	if (maxpages > swap_header->info.last_page) {
 		maxpages = swap_header->info.last_page + 1;
 		/* p->max is an unsigned int: don't overflow it */