Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 406 insertions, 0 deletions

diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
new file mode 100644
index 000000000..237dcdd73
--- /dev/null
+++ b/fs/kernfs/inode.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fs/kernfs/inode.c - kernfs inode implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ */
+
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+
+#include "kernfs-internal.h"
+
+static const struct inode_operations kernfs_iops = {
+	.permission	= kernfs_iop_permission,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.listxattr	= kernfs_iop_listxattr,
+};
+
+static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, bool alloc)
+{
+	struct kernfs_iattrs *ret __free(kfree) = NULL;
+	struct kernfs_iattrs *attr;
+
+	attr = READ_ONCE(kn->iattr);
+	if (attr || !alloc)
+		return attr;
+
+	ret = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	INIT_LIST_HEAD_RCU(&ret->xattrs);
+	/* assign default attributes */
+	ret->ia_uid = GLOBAL_ROOT_UID;
+	ret->ia_gid = GLOBAL_ROOT_GID;
+
+	ktime_get_real_ts64(&ret->ia_atime);
+	ret->ia_mtime = ret->ia_atime;
+	ret->ia_ctime = ret->ia_atime;
+
+	simple_xattr_limits_init(&ret->xattr_limits);
+
+	/* If someone raced us, recognize it. */
+	if (!try_cmpxchg(&kn->iattr, &attr, ret))
+		return READ_ONCE(kn->iattr);
+
+	return no_free_ptr(ret);
+}
+
+static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
+{
+	return __kernfs_iattrs(kn, true);
+}
+
+static struct kernfs_iattrs *kernfs_iattrs_noalloc(struct kernfs_node *kn)
+{
+	return __kernfs_iattrs(kn, false);
+}
+
+int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	struct kernfs_iattrs *attrs;
+	unsigned int ia_valid = iattr->ia_valid;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (ia_valid & ATTR_UID)
+		attrs->ia_uid = iattr->ia_uid;
+	if (ia_valid & ATTR_GID)
+		attrs->ia_gid = iattr->ia_gid;
+	if (ia_valid & ATTR_ATIME)
+		attrs->ia_atime = iattr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		attrs->ia_mtime = iattr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		attrs->ia_ctime = iattr->ia_ctime;
+	if (ia_valid & ATTR_MODE)
+		kn->mode = iattr->ia_mode;
+	return 0;
+}
+
+/**
+ * kernfs_setattr - set iattr on a node
+ * @kn: target node
+ * @iattr: iattr to set
+ *
+ * Return: %0 on success, -errno on failure.
+ */
+int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	int ret;
+	struct kernfs_root *root = kernfs_root(kn);
+
+	down_write(&root->kernfs_iattr_rwsem);
+	ret = __kernfs_setattr(kn, iattr);
+	up_write(&root->kernfs_iattr_rwsem);
+	return ret;
+}
+
+int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		       struct iattr *iattr)
+{
+	struct inode *inode = d_inode(dentry);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_root *root;
+	int error;
+
+	if (!kn)
+		return -EINVAL;
+
+	root = kernfs_root(kn);
+	down_write(&root->kernfs_iattr_rwsem);
+	error = setattr_prepare(&nop_mnt_idmap, dentry, iattr);
+	if (error)
+		goto out;
+
+	error = __kernfs_setattr(kn, iattr);
+	if (error)
+		goto out;
+
+	/* this ignores size changes */
+	setattr_copy(&nop_mnt_idmap, inode, iattr);
+
+out:
+	up_write(&root->kernfs_iattr_rwsem);
+	return error;
+}
+
+ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
+{
+	struct kernfs_node *kn = kernfs_dentry_node(dentry);
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs_noalloc(kn);
+	if (!attrs)
+		return 0;
+
+	return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size);
+}
+
+static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
+{
+	inode->i_mode = mode;
+	simple_inode_init_ts(inode);
+}
+
+static inline void set_inode_attr(struct inode *inode,
+				  struct kernfs_iattrs *attrs)
+{
+	inode->i_uid = attrs->ia_uid;
+	inode->i_gid = attrs->ia_gid;
+	inode_set_atime_to_ts(inode, attrs->ia_atime);
+	inode_set_mtime_to_ts(inode, attrs->ia_mtime);
+	inode_set_ctime_to_ts(inode, attrs->ia_ctime);
+}
+
+static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	struct kernfs_iattrs *attrs;
+
+	inode->i_mode = kn->mode;
+	attrs = kernfs_iattrs_noalloc(kn);
+	if (attrs)
+		/*
+		 * kernfs_node has non-default attributes get them from
+		 * persistent copy in kernfs_node.
+		 */
+		set_inode_attr(inode, attrs);
+
+	if (kernfs_type(kn) == KERNFS_DIR && !(kn->flags & KERNFS_REMOVING))
+		set_nlink(inode, kn->dir.subdirs + 2);
+}
+
+int kernfs_iop_getattr(struct mnt_idmap *idmap,
+		       const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_root *root = kernfs_root(kn);
+
+	down_read(&root->kernfs_iattr_rwsem);
+	kernfs_refresh_inode(kn, inode);
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	up_read(&root->kernfs_iattr_rwsem);
+
+	return 0;
+}
+
+static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	kernfs_get(kn);
+	inode->i_private = kn;
+	inode->i_mapping->a_ops = &ram_aops;
+	inode->i_op = &kernfs_iops;
+	inode->i_generation = kernfs_gen(kn);
+
+	set_default_inode_attr(inode, kn->mode);
+	kernfs_refresh_inode(kn, inode);
+
+	/* initialize inode according to type */
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		inode->i_op = &kernfs_dir_iops;
+		inode->i_fop = &kernfs_dir_fops;
+		if (kn->flags & KERNFS_EMPTY_DIR)
+			make_empty_dir_inode(inode);
+		break;
+	case KERNFS_FILE:
+		inode->i_size = kn->attr.size;
+		inode->i_fop = &kernfs_file_fops;
+		break;
+	case KERNFS_LINK:
+		inode->i_op = &kernfs_symlink_iops;
+		break;
+	default:
+		BUG();
+	}
+
+	unlock_new_inode(inode);
+}
+
+/**
+ *	kernfs_get_inode - get inode for kernfs_node
+ *	@sb: super block
+ *	@kn: kernfs_node to allocate inode for
+ *
+ *	Get inode for @kn.  If such inode doesn't exist, a new inode is
+ *	allocated and basics are initialized.  New inode is returned
+ *	locked.
+ *
+ *	Locking:
+ *	Kernel thread context (may sleep).
+ *
+ *	Return:
+ *	Pointer to allocated inode on success, %NULL on failure.
+ */
+struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
+{
+	struct inode *inode;
+
+	inode = iget_locked(sb, kernfs_ino(kn));
+	if (inode && (inode_state_read_once(inode) & I_NEW))
+		kernfs_init_inode(kn, inode);
+
+	return inode;
+}
+
+/*
+ * The kernfs_node serves as both an inode and a directory entry for
+ * kernfs.  To prevent the kernfs inode numbers from being freed
+ * prematurely we take a reference to kernfs_node from the kernfs inode.  A
+ * super_operations.evict_inode() implementation is needed to drop that
+ * reference upon inode destruction.
+ */
+void kernfs_evict_inode(struct inode *inode)
+{
+	struct kernfs_node *kn = inode->i_private;
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	kernfs_put(kn);
+}
+
+int kernfs_iop_permission(struct mnt_idmap *idmap,
+			  struct inode *inode, int mask)
+{
+	struct kernfs_node *kn;
+	struct kernfs_root *root;
+	int ret;
+
+	if (mask & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	kn = inode->i_private;
+	root = kernfs_root(kn);
+
+	down_read(&root->kernfs_iattr_rwsem);
+	kernfs_refresh_inode(kn, inode);
+	ret = generic_permission(&nop_mnt_idmap, inode, mask);
+	up_read(&root->kernfs_iattr_rwsem);
+
+	return ret;
+}
+
+int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
+		     void *value, size_t size)
+{
+	struct kernfs_iattrs *attrs = kernfs_iattrs_noalloc(kn);
+	struct simple_xattr_cache *cache = &kernfs_root(kn)->xa_cache;
+
+	if (!attrs)
+		return -ENODATA;
+
+	return simple_xattr_get(cache, &attrs->xattrs, name, value, size);
+}
+
+int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
+		     const void *value, size_t size, int flags)
+{
+	struct simple_xattr *old_xattr;
+	struct kernfs_iattrs *attrs;
+	struct simple_xattr_cache *cache = &kernfs_root(kn)->xa_cache;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	/*
+	 * Protect xattr modifications with the hashed per-node mutex.
+	 * Multiple superblocks (with different namespaces) can share the same
+	 * kernfs_node, so inode locking alone is insufficient. The hashed mutex
+	 * ensures serialization of concurrent xattr operations on the same node,
+	 * including the lazy allocation of the xattrs structure itself.
+	 */
+	CLASS(kernfs_node_lock, lock)(kn);
+
+	old_xattr = simple_xattr_set(cache, &attrs->xattrs, name, value, size, flags);
+	if (IS_ERR(old_xattr))
+		return PTR_ERR(old_xattr);
+
+	simple_xattr_free_rcu(old_xattr);
+	return 0;
+}
+
+static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
+				struct dentry *unused, struct inode *inode,
+				const char *suffix, void *value, size_t size)
+{
+	const char *name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+
+	return kernfs_xattr_get(kn, name, value, size);
+}
+
+static int kernfs_vfs_xattr_set(const struct xattr_handler *handler,
+				struct mnt_idmap *idmap,
+				struct dentry *unused, struct inode *inode,
+				const char *suffix, const void *value,
+				size_t size, int flags)
+{
+	const char *name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+
+	return kernfs_xattr_set(kn, name, value, size, flags);
+}
+
+static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,
+				     struct mnt_idmap *idmap,
+				     struct dentry *unused, struct inode *inode,
+				     const char *suffix, const void *value,
+				     size_t size, int flags)
+{
+	const char *full_name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_iattrs *attrs;
+
+	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_SUPPORT_USER_XATTR))
+		return -EOPNOTSUPP;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	/* See comment in kernfs_xattr_set() about locking. */
+	CLASS(kernfs_node_lock, lock)(kn);
+
+	return simple_xattr_set_limited(&kernfs_root(kn)->xa_cache,
+					&attrs->xattrs, &attrs->xattr_limits,
+					full_name, value, size, flags);
+}
+
+static const struct xattr_handler kernfs_trusted_xattr_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_xattr_set,
+};
+
+static const struct xattr_handler kernfs_security_xattr_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_xattr_set,
+};
+
+static const struct xattr_handler kernfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_user_xattr_set,
+};
+
+const struct xattr_handler * const kernfs_xattr_handlers[] = {
+	&kernfs_trusted_xattr_handler,
+	&kernfs_security_xattr_handler,
+	&kernfs_user_xattr_handler,
+	NULL
+};