Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "A lot of stuff, sorry about that. A week on a beach, then a bunch of
  time catching up then more time letting it bake in -next. Shan't do
  that again!"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (51 commits)
  include/linux/fs.h: fix comment about struct address_space
  checkpatch: fix ignoring cover-letter logic
  m32r: fix build failure
  lib/ratelimit.c: use deferred printk() version
  kernel/params.c: improve STANDARD_PARAM_DEF readability
  kernel/params.c: fix an overflow in param_attr_show
  kernel/params.c: fix the maximum length in param_get_string
  mm/memory_hotplug: define find_{smallest|biggest}_section_pfn as unsigned long
  mm/memory_hotplug: change pfn_to_section_nr/section_nr_to_pfn macro to inline function
  kernel/kcmp.c: drop branch leftover typo
  memremap: add scheduling point to devm_memremap_pages
  mm, page_alloc: add scheduling point to memmap_init_zone
  mm, memory_hotplug: add scheduling point to __add_pages
  lib/idr.c: fix comment for idr_replace()
  mm: memcontrol: use vmalloc fallback for large kmem memcg arrays
  kernel/sysctl.c: remove duplicate UINT_MAX check on do_proc_douintvec_conv()
  include/linux/bitfield.h: remove 32bit from FIELD_GET comment block
  lib/lz4: make arrays static const, reduces object code size
  exec: binfmt_misc: kill the onstack iname[BINPRM_BUF_SIZE] array
  exec: binfmt_misc: fix race between load_misc_binary() and kill_node()
  ...

4 files changed, 92 insertions, 49 deletions

diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index ce7181ea60fa..2a46762def31 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -54,7 +54,7 @@ typedef struct {
 	int size;			/* size of magic/mask */
 	char *magic;			/* magic or filename extension */
 	char *mask;			/* mask, NULL for exact match */
-	char *interpreter;		/* filename of interpreter */
+	const char *interpreter;	/* filename of interpreter */
 	char *name;
 	struct dentry *dentry;
 	struct file *interp_file;
@@ -131,27 +131,26 @@ static int load_misc_binary(struct linux_binprm *bprm)
 {
 	Node *fmt;
 	struct file *interp_file = NULL;
-	char iname[BINPRM_BUF_SIZE];
-	const char *iname_addr = iname;
 	int retval;
 	int fd_binary = -1;
 
 	retval = -ENOEXEC;
 	if (!enabled)
-		goto ret;
+		return retval;
 
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
 	if (fmt)
-		strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
+		dget(fmt->dentry);
 	read_unlock(&entries_lock);
 	if (!fmt)
-		goto ret;
+		return retval;
 
 	/* Need to be able to load the file after exec */
+	retval = -ENOENT;
 	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
-		return -ENOENT;
+		goto ret;
 
 	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
 		retval = remove_arg_zero(bprm);
@@ -195,22 +194,22 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	bprm->argc++;
 
 	/* add the interp as argv[0] */
-	retval = copy_strings_kernel(1, &iname_addr, bprm);
+	retval = copy_strings_kernel(1, &fmt->interpreter, bprm);
 	if (retval < 0)
 		goto error;
 	bprm->argc++;
 
 	/* Update interp in case binfmt_script needs it. */
-	retval = bprm_change_interp(iname, bprm);
+	retval = bprm_change_interp(fmt->interpreter, bprm);
 	if (retval < 0)
 		goto error;
 
-	if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) {
+	if (fmt->flags & MISC_FMT_OPEN_FILE) {
 		interp_file = filp_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
-		interp_file = open_exec(iname);
+		interp_file = open_exec(fmt->interpreter);
 	}
 	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
@@ -238,6 +237,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto error;
 
 ret:
+	dput(fmt->dentry);
 	return retval;
 error:
 	if (fd_binary > 0)
@@ -594,8 +594,13 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode)
 
 static void bm_evict_inode(struct inode *inode)
 {
+	Node *e = inode->i_private;
+
+	if (e->flags & MISC_FMT_OPEN_FILE)
+		filp_close(e->interp_file, NULL);
+
 	clear_inode(inode);
-	kfree(inode->i_private);
+	kfree(e);
 }
 
 static void kill_node(Node *e)
@@ -603,24 +608,14 @@ static void kill_node(Node *e)
 	struct dentry *dentry;
 
 	write_lock(&entries_lock);
-	dentry = e->dentry;
-	if (dentry) {
-		list_del_init(&e->list);
-		e->dentry = NULL;
-	}
+	list_del_init(&e->list);
 	write_unlock(&entries_lock);
 
-	if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) {
-		filp_close(e->interp_file, NULL);
-		e->interp_file = NULL;
-	}
-
-	if (dentry) {
-		drop_nlink(d_inode(dentry));
-		d_drop(dentry);
-		dput(dentry);
-		simple_release_fs(&bm_mnt, &entry_count);
-	}
+	dentry = e->dentry;
+	drop_nlink(d_inode(dentry));
+	d_drop(dentry);
+	dput(dentry);
+	simple_release_fs(&bm_mnt, &entry_count);
 }
 
 /* /<entry> */
@@ -665,7 +660,8 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 		root = file_inode(file)->i_sb->s_root;
 		inode_lock(d_inode(root));
 
-		kill_node(e);
+		if (!list_empty(&e->list))
+			kill_node(e);
 
 		inode_unlock(d_inode(root));
 		break;
@@ -794,7 +790,7 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer,
 		inode_lock(d_inode(root));
 
 		while (!list_empty(&entries))
-			kill_node(list_entry(entries.next, Node, list));
+			kill_node(list_first_entry(&entries, Node, list));
 
 		inode_unlock(d_inode(root));
 		break;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index afdf4e3cafc2..7cde3f46ad26 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -19,7 +19,6 @@ static int load_script(struct linux_binprm *bprm)
 	const char *i_arg, *i_name;
 	char *cp;
 	struct file *file;
-	char interp[BINPRM_BUF_SIZE];
 	int retval;
 
 	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
@@ -55,7 +54,7 @@ static int load_script(struct linux_binprm *bprm)
 			break;
 	}
 	for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++);
-	if (*cp == '\0') 
+	if (*cp == '\0')
 		return -ENOEXEC; /* No interpreter name found */
 	i_name = cp;
 	i_arg = NULL;
@@ -65,7 +64,6 @@ static int load_script(struct linux_binprm *bprm)
 		*cp++ = '\0';
 	if (*cp)
 		i_arg = cp;
-	strcpy (interp, i_name);
 	/*
 	 * OK, we've parsed out the interpreter name and
 	 * (optional) argument.
@@ -80,24 +78,27 @@ static int load_script(struct linux_binprm *bprm)
 	if (retval)
 		return retval;
 	retval = copy_strings_kernel(1, &bprm->interp, bprm);
-	if (retval < 0) return retval; 
+	if (retval < 0)
+		return retval;
 	bprm->argc++;
 	if (i_arg) {
 		retval = copy_strings_kernel(1, &i_arg, bprm);
-		if (retval < 0) return retval; 
+		if (retval < 0)
+			return retval;
 		bprm->argc++;
 	}
 	retval = copy_strings_kernel(1, &i_name, bprm);
-	if (retval) return retval; 
+	if (retval)
+		return retval;
 	bprm->argc++;
-	retval = bprm_change_interp(interp, bprm);
+	retval = bprm_change_interp(i_name, bprm);
 	if (retval < 0)
 		return retval;
 
 	/*
 	 * OK, now restart the process with the interpreter's dentry.
 	 */
-	file = open_exec(interp);
+	file = open_exec(i_name);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
diff --git a/fs/exec.c b/fs/exec.c
index ac34d9724684..5470d3c1892a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1410,7 +1410,7 @@ static void free_bprm(struct linux_binprm *bprm)
 	kfree(bprm);
 }
 
-int bprm_change_interp(char *interp, struct linux_binprm *bprm)
+int bprm_change_interp(const char *interp, struct linux_binprm *bprm)
 {
 	/* If a binfmt changed the interp, free it first. */
 	if (bprm->interp != bprm->filename)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ef4b48d1ea42..1c713fd5b3e6 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -588,6 +588,12 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 			break;
 		if (ACCESS_ONCE(ctx->released) ||
 		    fatal_signal_pending(current)) {
+			/*
+			 * &ewq->wq may be queued in fork_event, but
+			 * __remove_wait_queue ignores the head
+			 * parameter. It would be a problem if it
+			 * didn't.
+			 */
 			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
 			if (ewq->msg.event == UFFD_EVENT_FORK) {
 				struct userfaultfd_ctx *new;
@@ -1061,6 +1067,12 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 					(unsigned long)
 					uwq->msg.arg.reserved.reserved1;
 				list_move(&uwq->wq.entry, &fork_event);
+				/*
+				 * fork_nctx can be freed as soon as
+				 * we drop the lock, unless we take a
+				 * reference on it.
+				 */
+				userfaultfd_ctx_get(fork_nctx);
 				spin_unlock(&ctx->event_wqh.lock);
 				ret = 0;
 				break;
@@ -1091,19 +1103,53 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 
 	if (!ret && msg->event == UFFD_EVENT_FORK) {
 		ret = resolve_userfault_fork(ctx, fork_nctx, msg);
+		spin_lock(&ctx->event_wqh.lock);
+		if (!list_empty(&fork_event)) {
+			/*
+			 * The fork thread didn't abort, so we can
+			 * drop the temporary refcount.
+			 */
+			userfaultfd_ctx_put(fork_nctx);
+
+			uwq = list_first_entry(&fork_event,
+					       typeof(*uwq),
+					       wq.entry);
+			/*
+			 * If fork_event list wasn't empty and in turn
+			 * the event wasn't already released by fork
+			 * (the event is allocated on fork kernel
+			 * stack), put the event back to its place in
+			 * the event_wq. fork_event head will be freed
+			 * as soon as we return so the event cannot
+			 * stay queued there no matter the current
+			 * "ret" value.
+			 */
+			list_del(&uwq->wq.entry);
+			__add_wait_queue(&ctx->event_wqh, &uwq->wq);
 
-		if (!ret) {
-			spin_lock(&ctx->event_wqh.lock);
-			if (!list_empty(&fork_event)) {
-				uwq = list_first_entry(&fork_event,
-						       typeof(*uwq),
-						       wq.entry);
-				list_del(&uwq->wq.entry);
-				__add_wait_queue(&ctx->event_wqh, &uwq->wq);
+			/*
+			 * Leave the event in the waitqueue and report
+			 * error to userland if we failed to resolve
+			 * the userfault fork.
+			 */
+			if (likely(!ret))
 				userfaultfd_event_complete(ctx, uwq);
-			}
-			spin_unlock(&ctx->event_wqh.lock);
+		} else {
+			/*
+			 * Here the fork thread aborted and the
+			 * refcount from the fork thread on fork_nctx
+			 * has already been released. We still hold
+			 * the reference we took before releasing the
+			 * lock above. If resolve_userfault_fork
+			 * failed we've to drop it because the
+			 * fork_nctx has to be freed in such case. If
+			 * it succeeded we'll hold it because the new
+			 * uffd references it.
+			 */
+			if (ret)
+				userfaultfd_ctx_put(fork_nctx);
 		}
+		spin_unlock(&ctx->event_wqh.lock);
 	}
 
 	return ret;