Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "8 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  fs/exec.c: account for argv/envp pointers
  ocfs2: fix deadlock caused by recursive locking in xattr
  slub: make sysfs file removal asynchronous
  lib/cmdline.c: fix get_options() overflow while parsing ranges
  fs/dax.c: fix inefficiency in dax_writeback_mapping_range()
  autofs: sanity check status reported with AUTOFS_DEV_IOCTL_FAIL
  mm/vmalloc.c: huge-vmap: fail gracefully on unexpected huge vmap mappings
  mm, thp: remove cond_resched from __collapse_huge_page_copy

10 files changed, 86 insertions, 35 deletions

diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 734cbf8d9676..dd9f1bebb5a3 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -344,7 +344,7 @@ static int autofs_dev_ioctl_fail(struct file *fp,
 	int status;
 
 	token = (autofs_wqt_t) param->fail.token;
-	status = param->fail.status ? param->fail.status : -ENOENT;
+	status = param->fail.status < 0 ? param->fail.status : -ENOENT;
 	return autofs4_wait_release(sbi, token, status);
 }
 
diff --git a/fs/dax.c b/fs/dax.c
index 2a6889b3585f..9187f3b07f3e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -859,6 +859,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 			if (ret < 0)
 				goto out;
 		}
+		start_index = indices[pvec.nr - 1] + 1;
 	}
 out:
 	put_dax(dax_dev);
diff --git a/fs/exec.c b/fs/exec.c
index 72934df68471..904199086490 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -220,8 +220,26 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 
 	if (write) {
 		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
+		unsigned long ptr_size;
 		struct rlimit *rlim;
 
+		/*
+		 * Since the stack will hold pointers to the strings, we
+		 * must account for them as well.
+		 *
+		 * The size calculation is the entire vma while each arg page is
+		 * built, so each time we get here it's calculating how far it
+		 * is currently (rather than each call being just the newly
+		 * added size from the arg page).  As a result, we need to
+		 * always add the entire size of the pointers, so that on the
+		 * last call to get_arg_page() we'll actually have the entire
+		 * correct size.
+		 */
+		ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+		if (ptr_size > ULONG_MAX - size)
+			goto fail;
+		size += ptr_size;
+
 		acct_arg_size(bprm, size / PAGE_SIZE);
 
 		/*
@@ -239,13 +257,15 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 		 *    to work from.
 		 */
 		rlim = current->signal->rlim;
-		if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
-			put_page(page);
-			return NULL;
-		}
+		if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4)
+			goto fail;
 	}
 
 	return page;
+
+fail:
+	put_page(page);
+	return NULL;
 }
 
 static void put_arg_page(struct page *page)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 3b7c937a36b5..4689940a953c 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2591,6 +2591,10 @@ void ocfs2_inode_unlock_tracker(struct inode *inode,
 	struct ocfs2_lock_res *lockres;
 
 	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	/* had_lock means that the currect process already takes the cluster
+	 * lock previously. If had_lock is 1, we have nothing to do here, and
+	 * it will get unlocked where we got the lock.
+	 */
 	if (!had_lock) {
 		ocfs2_remove_holder(lockres, oh);
 		ocfs2_inode_unlock(inode, ex);
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 3c5384d9b3a5..f70c3778d600 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1328,20 +1328,21 @@ static int ocfs2_xattr_get(struct inode *inode,
 			   void *buffer,
 			   size_t buffer_size)
 {
-	int ret;
+	int ret, had_lock;
 	struct buffer_head *di_bh = NULL;
+	struct ocfs2_lock_holder oh;
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 0);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh);
+	if (had_lock < 0) {
+		mlog_errno(had_lock);
+		return had_lock;
 	}
 	down_read(&OCFS2_I(inode)->ip_xattr_sem);
 	ret = ocfs2_xattr_get_nolock(inode, di_bh, name_index,
 				     name, buffer, buffer_size);
 	up_read(&OCFS2_I(inode)->ip_xattr_sem);
 
-	ocfs2_inode_unlock(inode, 0);
+	ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock);
 
 	brelse(di_bh);
 
@@ -3537,11 +3538,12 @@ int ocfs2_xattr_set(struct inode *inode,
 {
 	struct buffer_head *di_bh = NULL;
 	struct ocfs2_dinode *di;
-	int ret, credits, ref_meta = 0, ref_credits = 0;
+	int ret, credits, had_lock, ref_meta = 0, ref_credits = 0;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, NULL, };
 	struct ocfs2_refcount_tree *ref_tree = NULL;
+	struct ocfs2_lock_holder oh;
 
 	struct ocfs2_xattr_info xi = {
 		.xi_name_index = name_index,
@@ -3572,8 +3574,9 @@ int ocfs2_xattr_set(struct inode *inode,
 		return -ENOMEM;
 	}
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (ret < 0) {
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 1, &oh);
+	if (had_lock < 0) {
+		ret = had_lock;
 		mlog_errno(ret);
 		goto cleanup_nolock;
 	}
@@ -3670,7 +3673,7 @@ cleanup:
 		if (ret)
 			mlog_errno(ret);
 	}
-	ocfs2_inode_unlock(inode, 1);
+	ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
 cleanup_nolock:
 	brelse(di_bh);
 	brelse(xbs.xattr_bh);
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 07ef550c6627..93315d6b21a8 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -84,6 +84,7 @@ struct kmem_cache {
 	int red_left_pad;	/* Left redzone padding size */
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
+	struct work_struct kobj_remove_work;
 #endif
 #ifdef CONFIG_MEMCG
 	struct memcg_cache_params memcg_params;
diff --git a/lib/cmdline.c b/lib/cmdline.c
index 3c6432df7e63..4c0888c4a68d 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -23,14 +23,14 @@
  *	the values[M, M+1, ..., N] into the ints array in get_options.
  */
 
-static int get_range(char **str, int *pint)
+static int get_range(char **str, int *pint, int n)
 {
 	int x, inc_counter, upper_range;
 
 	(*str)++;
 	upper_range = simple_strtol((*str), NULL, 0);
 	inc_counter = upper_range - *pint;
-	for (x = *pint; x < upper_range; x++)
+	for (x = *pint; n && x < upper_range; x++, n--)
 		*pint++ = x;
 	return inc_counter;
 }
@@ -97,7 +97,7 @@ char *get_options(const char *str, int nints, int *ints)
 			break;
 		if (res == 3) {
 			int range_nums;
-			range_nums = get_range((char **)&str, ints + i);
+			range_nums = get_range((char **)&str, ints + i, nints - i);
 			if (range_nums < 0)
 				break;
 			/*
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 945fd1ca49b5..df4ebdb2b10a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -652,7 +652,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 			spin_unlock(ptl);
 			free_page_and_swap_cache(src_page);
 		}
-		cond_resched();
 	}
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index 7449593fca72..8addc535bcdc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5625,6 +5625,28 @@ static char *create_unique_id(struct kmem_cache *s)
 	return name;
 }
 
+static void sysfs_slab_remove_workfn(struct work_struct *work)
+{
+	struct kmem_cache *s =
+		container_of(work, struct kmem_cache, kobj_remove_work);
+
+	if (!s->kobj.state_in_sysfs)
+		/*
+		 * For a memcg cache, this may be called during
+		 * deactivation and again on shutdown.  Remove only once.
+		 * A cache is never shut down before deactivation is
+		 * complete, so no need to worry about synchronization.
+		 */
+		return;
+
+#ifdef CONFIG_MEMCG
+	kset_unregister(s->memcg_kset);
+#endif
+	kobject_uevent(&s->kobj, KOBJ_REMOVE);
+	kobject_del(&s->kobj);
+	kobject_put(&s->kobj);
+}
+
 static int sysfs_slab_add(struct kmem_cache *s)
 {
 	int err;
@@ -5632,6 +5654,8 @@ static int sysfs_slab_add(struct kmem_cache *s)
 	struct kset *kset = cache_kset(s);
 	int unmergeable = slab_unmergeable(s);
 
+	INIT_WORK(&s->kobj_remove_work, sysfs_slab_remove_workfn);
+
 	if (!kset) {
 		kobject_init(&s->kobj, &slab_ktype);
 		return 0;
@@ -5695,20 +5719,8 @@ static void sysfs_slab_remove(struct kmem_cache *s)
 		 */
 		return;
 
-	if (!s->kobj.state_in_sysfs)
-		/*
-		 * For a memcg cache, this may be called during
-		 * deactivation and again on shutdown.  Remove only once.
-		 * A cache is never shut down before deactivation is
-		 * complete, so no need to worry about synchronization.
-		 */
-		return;
-
-#ifdef CONFIG_MEMCG
-	kset_unregister(s->memcg_kset);
-#endif
-	kobject_uevent(&s->kobj, KOBJ_REMOVE);
-	kobject_del(&s->kobj);
+	kobject_get(&s->kobj);
+	schedule_work(&s->kobj_remove_work);
 }
 
 void sysfs_slab_release(struct kmem_cache *s)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 34a1c3e46ed7..ecc97f74ab18 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -287,10 +287,21 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 	if (p4d_none(*p4d))
 		return NULL;
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud))
+
+	/*
+	 * Don't dereference bad PUD or PMD (below) entries. This will also
+	 * identify huge mappings, which we may encounter on architectures
+	 * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
+	 * identified as vmalloc addresses by is_vmalloc_addr(), but are
+	 * not [unambiguously] associated with a struct page, so there is
+	 * no correct value to return for them.
+	 */
+	WARN_ON_ONCE(pud_bad(*pud));
+	if (pud_none(*pud) || pud_bad(*pud))
 		return NULL;
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	WARN_ON_ONCE(pmd_bad(*pmd));
+	if (pmd_none(*pmd) || pmd_bad(*pmd))
 		return NULL;
 
 	ptep = pte_offset_map(pmd, addr);