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, 366 insertions, 0 deletions

diff --git a/fs/backing-file.c b/fs/backing-file.c
new file mode 100644
index 000000000..cc101143f
--- /dev/null
+++ b/fs/backing-file.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Forked from fs/overlayfs/file.c.
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#include <linux/fs.h>
+#include <linux/backing-file.h>
+#include <linux/splice.h>
+#include <linux/mm.h>
+#include <linux/security.h>
+
+#include "internal.h"
+
+/**
+ * backing_file_open - open a backing file for kernel internal use
+ * @user_file:  file the user requested to open
+ * @flags:	open flags
+ * @real_path:	path of the backing file
+ * @cred:	credentials for open
+ *
+ * Open a backing file for a stackable filesystem (e.g., overlayfs).
+ * @user_file->f_path may be on the stackable filesystem and @real_path
+ * on the underlying filesystem. In this case, we want to be able to
+ * return the path of the stackable filesystem. This is done by
+ * embedding the returned file into a container structure that also
+ * stores the stacked file's path, which can be retrieved using
+ * backing_file_user_path().
+ */
+struct file *backing_file_open(const struct file *user_file, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred)
+{
+	const struct path *user_path = file_user_path(user_file);
+	struct file *f;
+	int error;
+
+	f = alloc_empty_backing_file(flags, cred, user_file);
+	if (IS_ERR(f))
+		return f;
+
+	path_get(user_path);
+	backing_file_set_user_path(f, user_path);
+	error = vfs_open(real_path, f);
+	if (error) {
+		fput(f);
+		f = ERR_PTR(error);
+	}
+
+	return f;
+}
+EXPORT_SYMBOL_GPL(backing_file_open);
+
+struct file *backing_tmpfile_open(const struct file *user_file, int flags,
+				  const struct path *real_parentpath,
+				  umode_t mode, const struct cred *cred)
+{
+	struct mnt_idmap *real_idmap = mnt_idmap(real_parentpath->mnt);
+	const struct path *user_path = &user_file->f_path;
+	struct file *f;
+	int error;
+
+	f = alloc_empty_backing_file(flags, cred, user_file);
+	if (IS_ERR(f))
+		return f;
+
+	path_get(user_path);
+	backing_file_set_user_path(f, user_path);
+	error = vfs_tmpfile(real_idmap, real_parentpath, f, mode);
+	if (error) {
+		fput(f);
+		f = ERR_PTR(error);
+	}
+	return f;
+}
+EXPORT_SYMBOL(backing_tmpfile_open);
+
+struct backing_aio {
+	struct kiocb iocb;
+	refcount_t ref;
+	struct kiocb *orig_iocb;
+	/* used for aio completion */
+	void (*end_write)(struct kiocb *iocb, ssize_t);
+	struct work_struct work;
+	long res;
+};
+
+static struct kmem_cache *backing_aio_cachep;
+
+#define BACKING_IOCB_MASK \
+	(IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND)
+
+static rwf_t iocb_to_rw_flags(int flags)
+{
+	return (__force rwf_t)(flags & BACKING_IOCB_MASK);
+}
+
+static void backing_aio_put(struct backing_aio *aio)
+{
+	if (refcount_dec_and_test(&aio->ref)) {
+		fput(aio->iocb.ki_filp);
+		kmem_cache_free(backing_aio_cachep, aio);
+	}
+}
+
+static void backing_aio_cleanup(struct backing_aio *aio, long res)
+{
+	struct kiocb *iocb = &aio->iocb;
+	struct kiocb *orig_iocb = aio->orig_iocb;
+
+	orig_iocb->ki_pos = iocb->ki_pos;
+	if (aio->end_write)
+		aio->end_write(orig_iocb, res);
+
+	backing_aio_put(aio);
+}
+
+static void backing_aio_rw_complete(struct kiocb *iocb, long res)
+{
+	struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+	struct kiocb *orig_iocb = aio->orig_iocb;
+
+	if (iocb->ki_flags & IOCB_WRITE)
+		kiocb_end_write(iocb);
+
+	backing_aio_cleanup(aio, res);
+	orig_iocb->ki_complete(orig_iocb, res);
+}
+
+static void backing_aio_complete_work(struct work_struct *work)
+{
+	struct backing_aio *aio = container_of(work, struct backing_aio, work);
+
+	backing_aio_rw_complete(&aio->iocb, aio->res);
+}
+
+static void backing_aio_queue_completion(struct kiocb *iocb, long res)
+{
+	struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+
+	/*
+	 * Punt to a work queue to serialize updates of mtime/size.
+	 */
+	aio->res = res;
+	INIT_WORK(&aio->work, backing_aio_complete_work);
+	queue_work(file_inode(aio->orig_iocb->ki_filp)->i_sb->s_dio_done_wq,
+		   &aio->work);
+}
+
+static int backing_aio_init_wq(struct kiocb *iocb)
+{
+	struct super_block *sb = file_inode(iocb->ki_filp)->i_sb;
+
+	if (sb->s_dio_done_wq)
+		return 0;
+
+	return sb_init_dio_done_wq(sb);
+}
+
+static int do_backing_file_read_iter(struct file *file, struct iov_iter *iter,
+				     struct kiocb *iocb, int flags)
+{
+	struct backing_aio *aio = NULL;
+	int ret;
+
+	if (is_sync_kiocb(iocb)) {
+		rwf_t rwf = iocb_to_rw_flags(flags);
+
+		return vfs_iter_read(file, iter, &iocb->ki_pos, rwf);
+	}
+
+	aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+	if (!aio)
+		return -ENOMEM;
+
+	aio->orig_iocb = iocb;
+	kiocb_clone(&aio->iocb, iocb, get_file(file));
+	aio->iocb.ki_complete = backing_aio_rw_complete;
+	refcount_set(&aio->ref, 2);
+	ret = vfs_iocb_iter_read(file, &aio->iocb, iter);
+	backing_aio_put(aio);
+	if (ret != -EIOCBQUEUED)
+		backing_aio_cleanup(aio, ret);
+	return ret;
+}
+
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+			       struct kiocb *iocb, int flags,
+			       struct backing_file_ctx *ctx)
+{
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	if (iocb->ki_flags & IOCB_DIRECT &&
+	    !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
+
+	scoped_with_creds(ctx->cred)
+		ret = do_backing_file_read_iter(file, iter, iocb, flags);
+
+	if (ctx->accessed)
+		ctx->accessed(iocb->ki_filp);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_read_iter);
+
+static int do_backing_file_write_iter(struct file *file, struct iov_iter *iter,
+				      struct kiocb *iocb, int flags,
+				      void (*end_write)(struct kiocb *, ssize_t))
+{
+	struct backing_aio *aio;
+	int ret;
+
+	if (is_sync_kiocb(iocb)) {
+		rwf_t rwf = iocb_to_rw_flags(flags);
+
+		ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf);
+		if (end_write)
+			end_write(iocb, ret);
+		return ret;
+	}
+
+	ret = backing_aio_init_wq(iocb);
+	if (ret)
+		return ret;
+
+	aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+	if (!aio)
+		return -ENOMEM;
+
+	aio->orig_iocb = iocb;
+	aio->end_write = end_write;
+	kiocb_clone(&aio->iocb, iocb, get_file(file));
+	aio->iocb.ki_flags = flags;
+	aio->iocb.ki_complete = backing_aio_queue_completion;
+	refcount_set(&aio->ref, 2);
+	ret = vfs_iocb_iter_write(file, &aio->iocb, iter);
+	backing_aio_put(aio);
+	if (ret != -EIOCBQUEUED)
+		backing_aio_cleanup(aio, ret);
+	return ret;
+}
+
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+				struct kiocb *iocb, int flags,
+				struct backing_file_ctx *ctx)
+{
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	ret = file_remove_privs(iocb->ki_filp);
+	if (ret)
+		return ret;
+
+	if (iocb->ki_flags & IOCB_DIRECT &&
+	    !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
+
+	scoped_with_creds(ctx->cred)
+		return do_backing_file_write_iter(file, iter, iocb, flags, ctx->end_write);
+}
+EXPORT_SYMBOL_GPL(backing_file_write_iter);
+
+ssize_t backing_file_splice_read(struct file *in, struct kiocb *iocb,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags,
+				 struct backing_file_ctx *ctx)
+{
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	scoped_with_creds(ctx->cred)
+		ret = vfs_splice_read(in, &iocb->ki_pos, pipe, len, flags);
+
+	if (ctx->accessed)
+		ctx->accessed(iocb->ki_filp);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_read);
+
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+				  struct file *out, struct kiocb *iocb,
+				  size_t len, unsigned int flags,
+				  struct backing_file_ctx *ctx)
+{
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!out->f_op->splice_write)
+		return -EINVAL;
+
+	ret = file_remove_privs(iocb->ki_filp);
+	if (ret)
+		return ret;
+
+	scoped_with_creds(ctx->cred) {
+		file_start_write(out);
+		ret = out->f_op->splice_write(pipe, out, &iocb->ki_pos, len, flags);
+		file_end_write(out);
+	}
+
+	if (ctx->end_write)
+		ctx->end_write(iocb, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_write);
+
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+		      struct backing_file_ctx *ctx)
+{
+	struct file *user_file = vma->vm_file;
+	int ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!can_mmap_file(file))
+		return -ENODEV;
+
+	vma_set_file(vma, file);
+
+	scoped_with_creds(ctx->cred) {
+		ret = security_mmap_backing_file(vma, file, user_file);
+		if (ret)
+			return ret;
+
+		ret = vfs_mmap(vma->vm_file, vma);
+	}
+
+	if (ctx->accessed)
+		ctx->accessed(user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_mmap);
+
+static int __init backing_aio_init(void)
+{
+	backing_aio_cachep = KMEM_CACHE(backing_aio, SLAB_HWCACHE_ALIGN);
+	if (!backing_aio_cachep)
+		return -ENOMEM;
+
+	return 0;
+}
+fs_initcall(backing_aio_init);