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, 133 insertions, 0 deletions

diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
new file mode 100644
index 000000000..303ed6c71
--- /dev/null
+++ b/fs/btrfs/bio.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2022 Christoph Hellwig.
+ */
+
+#ifndef BTRFS_BIO_H
+#define BTRFS_BIO_H
+
+#include <linux/types.h>
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include "tree-checker.h"
+
+struct btrfs_bio;
+struct btrfs_fs_info;
+struct btrfs_inode;
+
+#define BTRFS_BIO_INLINE_CSUM_SIZE	64
+
+typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
+
+/*
+ * Highlevel btrfs I/O structure.  It is allocated by btrfs_bio_alloc and
+ * passed to btrfs_submit_bbio() for mapping to the physical devices.
+ */
+struct btrfs_bio {
+	/*
+	 * Inode and offset into it that this I/O operates on.
+	 *
+	 * If the inode is a data one, csum verification and read-repair
+	 * will be done automatically.
+	 * If the inode is a metadata one, everything is handled by the caller.
+	 */
+	struct btrfs_inode *inode;
+	u64 file_offset;
+
+	union {
+		/*
+		 * For data reads: checksumming and original I/O information.
+		 * (for internal use in the btrfs_submit_bbio() machinery only)
+		 */
+		struct {
+			u8 *csum;
+			u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
+			struct bvec_iter saved_iter;
+		};
+
+		/*
+		 * For data writes:
+		 * - ordered extent covering the bio
+		 * - pointer to the checksums for this bio
+		 * - original physical address from the allocator
+		 *   (for zone append only)
+		 * - original logical address, used for checksumming fscrypt bios
+		 */
+		struct {
+			struct btrfs_ordered_extent *ordered;
+			struct btrfs_ordered_sum *sums;
+			struct work_struct csum_work;
+			struct completion csum_done;
+			struct bvec_iter csum_saved_iter;
+			u64 orig_physical;
+			u64 orig_logical;
+		};
+
+		/* For metadata reads: parentness verification. */
+		struct btrfs_tree_parent_check parent_check;
+	};
+
+	/* For internal use in read end I/O handling */
+	struct work_struct end_io_work;
+
+	/* End I/O information supplied to btrfs_bio_alloc */
+	btrfs_bio_end_io_t end_io;
+	void *private;
+
+	atomic_t pending_ios;
+	u16 mirror_num;
+
+	/* Save the first error status of split bio. */
+	blk_status_t status;
+
+	/* Use the commit root to look up csums (data read bio only). */
+	bool csum_search_commit_root:1;
+
+	/*
+	 * Since scrub will reuse btree inode, we need this flag to distinguish
+	 * scrub bios.
+	 */
+	bool is_scrub:1;
+
+	/* Whether the bio is coming from copy_remapped_data_io(). */
+	bool is_remap:1;
+
+	/* Whether the csum generation for data write is async. */
+	bool async_csum:1;
+
+	/* Whether the bio is written using zone append. */
+	bool can_use_append:1;
+
+	/*
+	 * This member must come last, bio_alloc_bioset will allocate enough
+	 * bytes for entire btrfs_bio but relies on bio being last.
+	 */
+	struct bio bio;
+};
+
+static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
+{
+	return container_of(bio, struct btrfs_bio, bio);
+}
+
+int __init btrfs_bioset_init(void);
+void __cold btrfs_bioset_exit(void);
+
+void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_inode *inode, u64 file_offset,
+		    btrfs_bio_end_io_t end_io, void *private);
+struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+				  struct btrfs_inode *inode, u64 file_offset,
+				  btrfs_bio_end_io_t end_io, void *private);
+void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status);
+
+/* Submit using blkcg_punt_bio_submit. */
+#define REQ_BTRFS_CGROUP_PUNT			REQ_FS_PRIVATE
+
+void btrfs_submit_bbio(struct btrfs_bio *bbio, int mirror_num);
+void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace);
+int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 fileoff,
+			    u32 length, u64 logical, const phys_addr_t paddrs[],
+			    unsigned int step, int mirror_num);
+
+#endif