Merge branch 'akpm' (patches from Andrew Morton)

Merge first patch-bomb from Andrew Morton:
 - Some pidns/fork/exec tweaks
 - OCFS2 updates
 - Most of MM - there remain quite a few memcg parts which depend on
   pending core cgroups changes.  Which might have been already merged -
   I'll check tomorrow...
 - Various misc stuff all over the place
 - A few block bits which I never got around to sending to Jens -
   relatively minor things.
 - MAINTAINERS maintenance
 - A small number of lib/ updates
 - checkpatch updates
 - epoll
 - firmware/dmi-scan
 - Some kprobes work for S390
 - drivers/rtc updates
 - hfsplus feature work
 - vmcore feature work
 - rbtree upgrades
 - AOE updates
 - pktcdvd cleanups
 - PPS
 - memstick
 - w1
 - New "inittmpfs" feature, which does the obvious
 - More IPC work from Davidlohr.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (303 commits)
  lz4: fix compression/decompression signedness mismatch
  ipc: drop ipc_lock_check
  ipc, shm: drop shm_lock_check
  ipc: drop ipc_lock_by_ptr
  ipc, shm: guard against non-existant vma in shmdt(2)
  ipc: document general ipc locking scheme
  ipc,msg: drop msg_unlock
  ipc: rename ids->rw_mutex
  ipc,shm: shorten critical region for shmat
  ipc,shm: cleanup do_shmat pasta
  ipc,shm: shorten critical region for shmctl
  ipc,shm: make shmctl_nolock lockless
  ipc,shm: introduce shmctl_nolock
  ipc: drop ipcctl_pre_down
  ipc,shm: shorten critical region in shmctl_down
  ipc,shm: introduce lockless functions to obtain the ipc object
  initmpfs: use initramfs if rootfstype= or root= specified
  initmpfs: make rootfs use tmpfs when CONFIG_TMPFS enabled
  initmpfs: move rootfs code from fs/ramfs/ to init/
  initmpfs: move bdi setup from init_rootfs to init_ramfs
  ...

1 files changed, 27 insertions, 32 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index f9c97d10b87..9d548512ff8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1202,7 +1202,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long *populate)
 {
 	struct mm_struct * mm = current->mm;
-	struct inode *inode;
 	vm_flags_t vm_flags;
 
 	*populate = 0;
@@ -1265,9 +1264,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			return -EAGAIN;
 	}
 
-	inode = file ? file_inode(file) : NULL;
-
 	if (file) {
+		struct inode *inode = file_inode(file);
+
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
 			if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
@@ -1302,6 +1301,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 
 			if (!file->f_op || !file->f_op->mmap)
 				return -ENODEV;
+			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+				return -EINVAL;
 			break;
 
 		default:
@@ -1310,6 +1311,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	} else {
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
+			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+				return -EINVAL;
 			/*
 			 * Ignore pgoff.
 			 */
@@ -1476,11 +1479,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	int correct_wcount = 0;
 	int error;
 	struct rb_node **rb_link, *rb_parent;
 	unsigned long charged = 0;
-	struct inode *inode =  file ? file_inode(file) : NULL;
 
 	/* Check against address space limit. */
 	if (!may_expand_vm(mm, len >> PAGE_SHIFT)) {
@@ -1544,16 +1545,11 @@ munmap_back:
 	vma->vm_pgoff = pgoff;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
-	error = -EINVAL;	/* when rejecting VM_GROWSDOWN|VM_GROWSUP */
-
 	if (file) {
-		if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
-			goto free_vma;
 		if (vm_flags & VM_DENYWRITE) {
 			error = deny_write_access(file);
 			if (error)
 				goto free_vma;
-			correct_wcount = 1;
 		}
 		vma->vm_file = get_file(file);
 		error = file->f_op->mmap(file, vma);
@@ -1570,11 +1566,8 @@ munmap_back:
 		WARN_ON_ONCE(addr != vma->vm_start);
 
 		addr = vma->vm_start;
-		pgoff = vma->vm_pgoff;
 		vm_flags = vma->vm_flags;
 	} else if (vm_flags & VM_SHARED) {
-		if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP)))
-			goto free_vma;
 		error = shmem_zero_setup(vma);
 		if (error)
 			goto free_vma;
@@ -1596,11 +1589,10 @@ munmap_back:
 	}
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
-	file = vma->vm_file;
-
 	/* Once vma denies write, undo our temporary denial count */
-	if (correct_wcount)
-		atomic_inc(&inode->i_writecount);
+	if (vm_flags & VM_DENYWRITE)
+		allow_write_access(file);
+	file = vma->vm_file;
 out:
 	perf_event_mmap(vma);
 
@@ -1616,11 +1608,20 @@ out:
 	if (file)
 		uprobe_mmap(vma);
 
+	/*
+	 * New (or expanded) vma always get soft dirty status.
+	 * Otherwise user-space soft-dirty page tracker won't
+	 * be able to distinguish situation when vma area unmapped,
+	 * then new mapped in-place (which must be aimed as
+	 * a completely new data area).
+	 */
+	vma->vm_flags |= VM_SOFTDIRTY;
+
 	return addr;
 
 unmap_and_free_vma:
-	if (correct_wcount)
-		atomic_inc(&inode->i_writecount);
+	if (vm_flags & VM_DENYWRITE)
+		allow_write_access(file);
 	vma->vm_file = NULL;
 	fput(file);
 
@@ -2380,7 +2381,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	      unsigned long addr, int new_below)
 {
-	struct mempolicy *pol;
 	struct vm_area_struct *new;
 	int err = -ENOMEM;
 
@@ -2404,12 +2404,9 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 		new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
 	}
 
-	pol = mpol_dup(vma_policy(vma));
-	if (IS_ERR(pol)) {
-		err = PTR_ERR(pol);
+	err = vma_dup_policy(vma, new);
+	if (err)
 		goto out_free_vma;
-	}
-	vma_set_policy(new, pol);
 
 	if (anon_vma_clone(new, vma))
 		goto out_free_mpol;
@@ -2437,7 +2434,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 		fput(new->vm_file);
 	unlink_anon_vmas(new);
  out_free_mpol:
-	mpol_put(pol);
+	mpol_put(vma_policy(new));
  out_free_vma:
 	kmem_cache_free(vm_area_cachep, new);
  out_err:
@@ -2663,6 +2660,7 @@ out:
 	mm->total_vm += len >> PAGE_SHIFT;
 	if (flags & VM_LOCKED)
 		mm->locked_vm += (len >> PAGE_SHIFT);
+	vma->vm_flags |= VM_SOFTDIRTY;
 	return addr;
 }
 
@@ -2780,7 +2778,6 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *new_vma, *prev;
 	struct rb_node **rb_link, *rb_parent;
-	struct mempolicy *pol;
 	bool faulted_in_anon_vma = true;
 
 	/*
@@ -2825,10 +2822,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			new_vma->vm_start = addr;
 			new_vma->vm_end = addr + len;
 			new_vma->vm_pgoff = pgoff;
-			pol = mpol_dup(vma_policy(vma));
-			if (IS_ERR(pol))
+			if (vma_dup_policy(vma, new_vma))
 				goto out_free_vma;
-			vma_set_policy(new_vma, pol);
 			INIT_LIST_HEAD(&new_vma->anon_vma_chain);
 			if (anon_vma_clone(new_vma, vma))
 				goto out_free_mempol;
@@ -2843,7 +2838,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 	return new_vma;
 
  out_free_mempol:
-	mpol_put(pol);
+	mpol_put(vma_policy(new_vma));
  out_free_vma:
 	kmem_cache_free(vm_area_cachep, new_vma);
 	return NULL;
@@ -2930,7 +2925,7 @@ int install_special_mapping(struct mm_struct *mm,
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 
-	vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND;
+	vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 
 	vma->vm_ops = &special_mapping_vmops;