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, 251 insertions, 0 deletions

diff --git a/fs/bad_inode.c b/fs/bad_inode.c
new file mode 100644
index 000000000..486c40f73
--- /dev/null
+++ b/fs/bad_inode.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/bad_inode.c
+ *
+ *  Copyright (C) 1997, Stephen Tweedie
+ *
+ *  Provide stub functions for unreadable inodes
+ *
+ *  Fabian Frederick : August 2003 - All file operations assigned to EIO
+ */
+
+#include <linux/fs.h>
+#include <linux/export.h>
+#include <linux/stat.h>
+#include <linux/time.h>
+#include <linux/namei.h>
+#include <linux/poll.h>
+#include <linux/fiemap.h>
+
+static int bad_file_open(struct inode *inode, struct file *filp)
+{
+	return -EIO;
+}
+
+static const struct file_operations bad_file_ops =
+{
+	.open		= bad_file_open,
+};
+
+static int bad_inode_create(struct mnt_idmap *idmap,
+			    struct inode *dir, struct dentry *dentry,
+			    umode_t mode)
+{
+	return -EIO;
+}
+
+static struct dentry *bad_inode_lookup(struct inode *dir,
+			struct dentry *dentry, unsigned int flags)
+{
+	return ERR_PTR(-EIO);
+}
+
+static int bad_inode_link (struct dentry *old_dentry, struct inode *dir,
+		struct dentry *dentry)
+{
+	return -EIO;
+}
+
+static int bad_inode_unlink(struct inode *dir, struct dentry *dentry)
+{
+	return -EIO;
+}
+
+static int bad_inode_symlink(struct mnt_idmap *idmap,
+			     struct inode *dir, struct dentry *dentry,
+			     const char *symname)
+{
+	return -EIO;
+}
+
+static struct dentry *bad_inode_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+				      struct dentry *dentry, umode_t mode)
+{
+	return ERR_PTR(-EIO);
+}
+
+static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry)
+{
+	return -EIO;
+}
+
+static int bad_inode_mknod(struct mnt_idmap *idmap, struct inode *dir,
+			   struct dentry *dentry, umode_t mode, dev_t rdev)
+{
+	return -EIO;
+}
+
+static int bad_inode_rename2(struct mnt_idmap *idmap,
+			     struct inode *old_dir, struct dentry *old_dentry,
+			     struct inode *new_dir, struct dentry *new_dentry,
+			     unsigned int flags)
+{
+	return -EIO;
+}
+
+static int bad_inode_readlink(struct dentry *dentry, char __user *buffer,
+		int buflen)
+{
+	return -EIO;
+}
+
+static int bad_inode_permission(struct mnt_idmap *idmap,
+				struct inode *inode, int mask)
+{
+	return -EIO;
+}
+
+static int bad_inode_getattr(struct mnt_idmap *idmap,
+			     const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
+{
+	return -EIO;
+}
+
+static int bad_inode_setattr(struct mnt_idmap *idmap,
+			     struct dentry *direntry, struct iattr *attrs)
+{
+	return -EIO;
+}
+
+static ssize_t bad_inode_listxattr(struct dentry *dentry, char *buffer,
+			size_t buffer_size)
+{
+	return -EIO;
+}
+
+static const char *bad_inode_get_link(struct dentry *dentry,
+				      struct inode *inode,
+				      struct delayed_call *done)
+{
+	return ERR_PTR(-EIO);
+}
+
+static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type, bool rcu)
+{
+	return ERR_PTR(-EIO);
+}
+
+static int bad_inode_fiemap(struct inode *inode,
+			    struct fiemap_extent_info *fieinfo, u64 start,
+			    u64 len)
+{
+	return -EIO;
+}
+
+static int bad_inode_update_time(struct inode *inode, enum fs_update_time type,
+				 unsigned int flags)
+{
+	return -EIO;
+}
+
+static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry,
+				 struct file *file, unsigned int open_flag,
+				 umode_t create_mode)
+{
+	return -EIO;
+}
+
+static int bad_inode_tmpfile(struct mnt_idmap *idmap,
+			     struct inode *inode, struct file *file,
+			     umode_t mode)
+{
+	return -EIO;
+}
+
+static int bad_inode_set_acl(struct mnt_idmap *idmap,
+			     struct dentry *dentry, struct posix_acl *acl,
+			     int type)
+{
+	return -EIO;
+}
+
+static const struct inode_operations bad_inode_ops =
+{
+	.create		= bad_inode_create,
+	.lookup		= bad_inode_lookup,
+	.link		= bad_inode_link,
+	.unlink		= bad_inode_unlink,
+	.symlink	= bad_inode_symlink,
+	.mkdir		= bad_inode_mkdir,
+	.rmdir		= bad_inode_rmdir,
+	.mknod		= bad_inode_mknod,
+	.rename		= bad_inode_rename2,
+	.readlink	= bad_inode_readlink,
+	.permission	= bad_inode_permission,
+	.getattr	= bad_inode_getattr,
+	.setattr	= bad_inode_setattr,
+	.listxattr	= bad_inode_listxattr,
+	.get_link	= bad_inode_get_link,
+	.get_inode_acl	= bad_inode_get_acl,
+	.fiemap		= bad_inode_fiemap,
+	.update_time	= bad_inode_update_time,
+	.atomic_open	= bad_inode_atomic_open,
+	.tmpfile	= bad_inode_tmpfile,
+	.set_acl	= bad_inode_set_acl,
+};
+
+
+/*
+ * When a filesystem is unable to read an inode due to an I/O error in
+ * its read_inode() function, it can call make_bad_inode() to return a
+ * set of stubs which will return EIO errors as required. 
+ *
+ * We only need to do limited initialisation: all other fields are
+ * preinitialised to zero automatically.
+ */
+ 
+/**
+ *	make_bad_inode - mark an inode bad due to an I/O error
+ *	@inode: Inode to mark bad
+ *
+ *	When an inode cannot be read due to a media or remote network
+ *	failure this function makes the inode "bad" and causes I/O operations
+ *	on it to fail from this point on.
+ */
+ 
+void make_bad_inode(struct inode *inode)
+{
+	remove_inode_hash(inode);
+
+	inode->i_mode = S_IFREG;
+	simple_inode_init_ts(inode);
+	inode->i_op = &bad_inode_ops;	
+	inode->i_opflags &= ~IOP_XATTR;
+	inode->i_fop = &bad_file_ops;	
+}
+EXPORT_SYMBOL(make_bad_inode);
+
+/*
+ * This tests whether an inode has been flagged as bad. The test uses
+ * &bad_inode_ops to cover the case of invalidated inodes as well as
+ * those created by make_bad_inode() above.
+ */
+ 
+/**
+ *	is_bad_inode - is an inode errored
+ *	@inode: inode to test
+ *
+ *	Returns true if the inode in question has been marked as bad.
+ */
+ 
+bool is_bad_inode(struct inode *inode)
+{
+	return (inode->i_op == &bad_inode_ops);	
+}
+
+EXPORT_SYMBOL(is_bad_inode);
+
+/**
+ * iget_failed - Mark an under-construction inode as dead and release it
+ * @inode: The inode to discard
+ *
+ * Mark an under-construction inode as dead and release it.
+ */
+void iget_failed(struct inode *inode)
+{
+	make_bad_inode(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+}
+EXPORT_SYMBOL(iget_failed);