Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

Conflicts:
	drivers/net/wireless/iwlwifi/iwl-agn.c
	drivers/net/wireless/iwlwifi/iwl3945-base.c

13 files changed, 89 insertions, 45 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index 736ba7f3306a..b6ec85abbb39 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -198,7 +198,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 			flags &= MAP_NONBLOCK;
 			get_file(file);
 			addr = mmap_region(file, start, size,
-					flags, vma->vm_flags, pgoff, 1);
+					flags, vma->vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 618e98304080..107da3d809a8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2269,12 +2269,18 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 
 int hugetlb_reserve_pages(struct inode *inode,
 					long from, long to,
-					struct vm_area_struct *vma)
+					struct vm_area_struct *vma,
+					int acctflag)
 {
 	long ret, chg;
 	struct hstate *h = hstate_inode(inode);
 
-	if (vma && vma->vm_flags & VM_NORESERVE)
+	/*
+	 * Only apply hugepage reservation if asked. At fault time, an
+	 * attempt will be made for VM_NORESERVE to allocate a page
+	 * and filesystem quota without using reserves
+	 */
+	if (acctflag & VM_NORESERVE)
 		return 0;
 
 	/*
@@ -2299,13 +2305,31 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (chg < 0)
 		return chg;
 
+	/* There must be enough filesystem quota for the mapping */
 	if (hugetlb_get_quota(inode->i_mapping, chg))
 		return -ENOSPC;
+
+	/*
+	 * Check enough hugepages are available for the reservation.
+	 * Hand back the quota if there are not
+	 */
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugetlb_put_quota(inode->i_mapping, chg);
 		return ret;
 	}
+
+	/*
+	 * Account for the reservations made. Shared mappings record regions
+	 * that have reservations as they are shared by multiple VMAs.
+	 * When the last VMA disappears, the region map says how much
+	 * the reservation was and the page cache tells how much of
+	 * the reservation was consumed. Private mappings are per-VMA and
+	 * only the consumed reservations are tracked. When the VMA
+	 * disappears, the original reservation is the VMA size and the
+	 * consumed reservations are stored in the map. Hence, nothing
+	 * else has to be done for private mappings here
+	 */
 	if (!vma || vma->vm_flags & VM_SHARED)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
diff --git a/mm/memory.c b/mm/memory.c
index 22bfa7a47a0b..baa999e87cd2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1999,7 +1999,7 @@ gotten:
 	 * Don't let another task, with possibly unlocked vma,
 	 * keep the mlocked page.
 	 */
-	if (vma->vm_flags & VM_LOCKED) {
+	if ((vma->vm_flags & VM_LOCKED) && old_page) {
 		lock_page(old_page);	/* for LRU manipulation */
 		clear_page_mlock(old_page);
 		unlock_page(old_page);
diff --git a/mm/migrate.c b/mm/migrate.c
index 2bb4e1d63520..a9eff3f092f6 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1129,7 +1129,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
  	struct vm_area_struct *vma;
  	int err = 0;
 
- 	for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) {
+	for (vma = mm->mmap; vma && !err; vma = vma->vm_next) {
  		if (vma->vm_ops && vma->vm_ops->migrate) {
  			err = vma->vm_ops->migrate(vma, to, from, flags);
  			if (err)
diff --git a/mm/mlock.c b/mm/mlock.c
index 028ec482fdd4..037161d61b4e 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -311,7 +311,10 @@ long mlock_vma_pages_range(struct vm_area_struct *vma,
 			is_vm_hugetlb_page(vma) ||
 			vma == get_gate_vma(current))) {
 
-		return __mlock_vma_pages_range(vma, start, end, 1);
+		__mlock_vma_pages_range(vma, start, end, 1);
+
+		/* Hide errors from mmap() and other callers */
+		return 0;
 	}
 
 	/*
diff --git a/mm/mmap.c b/mm/mmap.c
index 214b6a258eeb..00ced3ee49a8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -918,7 +918,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	struct inode *inode;
 	unsigned int vm_flags;
 	int error;
-	int accountable = 1;
 	unsigned long reqprot = prot;
 
 	/*
@@ -1019,8 +1018,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 					return -EPERM;
 				vm_flags &= ~VM_MAYEXEC;
 			}
-			if (is_file_hugepages(file))
-				accountable = 0;
 
 			if (!file->f_op || !file->f_op->mmap)
 				return -ENODEV;
@@ -1053,8 +1050,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	if (error)
 		return error;
 
-	return mmap_region(file, addr, len, flags, vm_flags, pgoff,
-			   accountable);
+	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
@@ -1092,17 +1088,23 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 
 /*
  * We account for memory if it's a private writeable mapping,
- * and VM_NORESERVE wasn't set.
+ * not hugepages and VM_NORESERVE wasn't set.
  */
-static inline int accountable_mapping(unsigned int vm_flags)
+static inline int accountable_mapping(struct file *file, unsigned int vm_flags)
 {
+	/*
+	 * hugetlb has its own accounting separate from the core VM
+	 * VM_HUGETLB may not be set yet so we cannot check for that flag.
+	 */
+	if (file && is_file_hugepages(file))
+		return 0;
+
 	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
 }
 
 unsigned long mmap_region(struct file *file, unsigned long addr,
 			  unsigned long len, unsigned long flags,
-			  unsigned int vm_flags, unsigned long pgoff,
-			  int accountable)
+			  unsigned int vm_flags, unsigned long pgoff)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
@@ -1128,18 +1130,22 @@ munmap_back:
 
 	/*
 	 * Set 'VM_NORESERVE' if we should not account for the
-	 * memory use of this mapping. We only honor MAP_NORESERVE
-	 * if we're allowed to overcommit memory.
+	 * memory use of this mapping.
 	 */
-	if ((flags & MAP_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER)
-		vm_flags |= VM_NORESERVE;
-	if (!accountable)
-		vm_flags |= VM_NORESERVE;
+	if ((flags & MAP_NORESERVE)) {
+		/* We honor MAP_NORESERVE if allowed to overcommit */
+		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+			vm_flags |= VM_NORESERVE;
+
+		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
+		if (file && is_file_hugepages(file))
+			vm_flags |= VM_NORESERVE;
+	}
 
 	/*
 	 * Private writable mapping: check memory availability
 	 */
-	if (accountable_mapping(vm_flags)) {
+	if (accountable_mapping(file, vm_flags)) {
 		charged = len >> PAGE_SHIFT;
 		if (security_vm_enough_memory(charged))
 			return -ENOMEM;
@@ -2078,12 +2084,8 @@ void exit_mmap(struct mm_struct *mm)
 	unsigned long end;
 
 	/* mm's last user has gone, and its about to be pulled down */
-	arch_exit_mmap(mm);
 	mmu_notifier_release(mm);
 
-	if (!mm->mmap)	/* Can happen if dup_mmap() received an OOM */
-		return;
-
 	if (mm->locked_vm) {
 		vma = mm->mmap;
 		while (vma) {
@@ -2092,7 +2094,13 @@ void exit_mmap(struct mm_struct *mm)
 			vma = vma->vm_next;
 		}
 	}
+
+	arch_exit_mmap(mm);
+
 	vma = mm->mmap;
+	if (!vma)	/* Can happen if dup_mmap() received an OOM */
+		return;
+
 	lru_add_drain();
 	flush_cache_mm(mm);
 	tlb = tlb_gather_mmu(mm, 1);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index abe2694e13f4..258197b76fb4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -151,10 +151,11 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
-	 * make it unwritable again.
+	 * make it unwritable again. hugetlb mapping were accounted for
+	 * even if read-only so there is no need to account for them here
 	 */
 	if (newflags & VM_WRITE) {
-		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|
+		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
 						VM_SHARED|VM_NORESERVE))) {
 			charged = nrpages;
 			if (security_vm_enough_memory(charged))
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index dc32dae01e5f..3c84128596ba 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -209,7 +209,7 @@ int dirty_bytes_handler(struct ctl_table *table, int write,
 		struct file *filp, void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
-	int old_bytes = vm_dirty_bytes;
+	unsigned long old_bytes = vm_dirty_bytes;
 	int ret;
 
 	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
@@ -1051,20 +1051,23 @@ continue_unlock:
 				}
  			}
 
-			if (nr_to_write > 0)
+			if (nr_to_write > 0) {
 				nr_to_write--;
-			else if (wbc->sync_mode == WB_SYNC_NONE) {
-				/*
-				 * We stop writing back only if we are not
-				 * doing integrity sync. In case of integrity
-				 * sync we have to keep going because someone
-				 * may be concurrently dirtying pages, and we
-				 * might have synced a lot of newly appeared
-				 * dirty pages, but have not synced all of the
-				 * old dirty pages.
-				 */
-				done = 1;
-				break;
+				if (nr_to_write == 0 &&
+				    wbc->sync_mode == WB_SYNC_NONE) {
+					/*
+					 * We stop writing back only if we are
+					 * not doing integrity sync. In case of
+					 * integrity sync we have to keep going
+					 * because someone may be concurrently
+					 * dirtying pages, and we might have
+					 * synced a lot of newly appeared dirty
+					 * pages, but have not synced all of the
+					 * old dirty pages.
+					 */
+					done = 1;
+					break;
+				}
 			}
 
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
@@ -1076,7 +1079,7 @@ continue_unlock:
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-	if (!cycled) {
+	if (!cycled && !done) {
 		/*
 		 * range_cyclic:
 		 * We hit the last page and there is more work to be done: wrap
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 7006a11350c8..ceecfbb143fa 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -114,7 +114,8 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn)
 		nid = page_to_nid(pfn_to_page(pfn));
 		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 		if (slab_is_available()) {
-			base = kmalloc_node(table_size, GFP_KERNEL, nid);
+			base = kmalloc_node(table_size,
+					GFP_KERNEL | __GFP_NOWARN, nid);
 			if (!base)
 				base = vmalloc_node(table_size, nid);
 		} else {
diff --git a/mm/rmap.c b/mm/rmap.c
index ac4af8cffbf9..16521664010d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1072,7 +1072,8 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
 	spin_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		if (MLOCK_PAGES && unlikely(unlock)) {
-			if (!(vma->vm_flags & VM_LOCKED))
+			if (!((vma->vm_flags & VM_LOCKED) &&
+						page_mapped_in_vma(page, vma)))
 				continue;	/* must visit all vmas */
 			ret = SWAP_MLOCK;
 		} else {
diff --git a/mm/slab.c b/mm/slab.c
index ddc41f337d58..4d00855629c4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4457,3 +4457,4 @@ size_t ksize(const void *objp)
 
 	return obj_size(virt_to_cache(objp));
 }
+EXPORT_SYMBOL(ksize);
diff --git a/mm/slob.c b/mm/slob.c
index bf7e8fc3aed8..52bc8a2bd9ef 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -521,6 +521,7 @@ size_t ksize(const void *block)
 	} else
 		return sp->page.private;
 }
+EXPORT_SYMBOL(ksize);
 
 struct kmem_cache {
 	unsigned int size, align;
diff --git a/mm/slub.c b/mm/slub.c
index bdc9abb08a23..0280eee6cf37 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2736,6 +2736,7 @@ size_t ksize(const void *object)
 	 */
 	return s->size;
 }
+EXPORT_SYMBOL(ksize);
 
 void kfree(const void *x)
 {