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, 244 insertions, 0 deletions

diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
new file mode 100644
index 000000000..4b39ed43a
--- /dev/null
+++ b/fs/nilfs2/segment.h
@@ -0,0 +1,244 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * NILFS Segment constructor prototypes and definitions
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * Written by Ryusuke Konishi.
+ *
+ */
+#ifndef _NILFS_SEGMENT_H
+#define _NILFS_SEGMENT_H
+
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/workqueue.h>
+#include "nilfs.h"
+
+struct nilfs_root;
+
+/**
+ * struct nilfs_recovery_info - Recovery information
+ * @ri_need_recovery: Recovery status
+ * @ri_super_root: Block number of the last super root
+ * @ri_cno: Number of the last checkpoint
+ * @ri_lsegs_start: Region for roll-forwarding (start block number)
+ * @ri_lsegs_end: Region for roll-forwarding (end block number)
+ * @ri_lsegs_start_seq: Sequence value of the segment at ri_lsegs_start
+ * @ri_used_segments: List of segments to be mark active
+ * @ri_pseg_start: Block number of the last partial segment
+ * @ri_seq: Sequence number on the last partial segment
+ * @ri_segnum: Segment number on the last partial segment
+ * @ri_nextnum: Next segment number on the last partial segment
+ */
+struct nilfs_recovery_info {
+	int			ri_need_recovery;
+	sector_t		ri_super_root;
+	__u64			ri_cno;
+
+	sector_t		ri_lsegs_start;
+	sector_t		ri_lsegs_end;
+	u64			ri_lsegs_start_seq;
+	struct list_head	ri_used_segments;
+	sector_t		ri_pseg_start;
+	u64			ri_seq;
+	__u64			ri_segnum;
+	__u64			ri_nextnum;
+};
+
+/* ri_need_recovery */
+#define NILFS_RECOVERY_SR_UPDATED	 1  /* The super root was updated */
+#define NILFS_RECOVERY_ROLLFORWARD_DONE	 2  /* Rollforward was carried out */
+
+/**
+ * struct nilfs_cstage - Context of collection stage
+ * @scnt: Stage count, must be accessed via wrappers:
+ *        nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get()
+ * @flags: State flags
+ * @dirty_file_ptr: Pointer on dirty_files list, or inode of a target file
+ * @gc_inode_ptr: Pointer on the list of gc-inodes
+ */
+struct nilfs_cstage {
+	int			scnt;
+	unsigned int		flags;
+	struct nilfs_inode_info *dirty_file_ptr;
+	struct nilfs_inode_info *gc_inode_ptr;
+};
+
+struct nilfs_segment_buffer;
+
+struct nilfs_segsum_pointer {
+	struct buffer_head     *bh;
+	unsigned int		offset; /* offset in bytes */
+};
+
+/**
+ * struct nilfs_sc_info - Segment constructor information
+ * @sc_super: Back pointer to super_block struct
+ * @sc_root: root object of the current filesystem tree
+ * @sc_nblk_inc: Block count of current generation
+ * @sc_dirty_files: List of files to be written
+ * @sc_gc_inodes: List of GC inodes having blocks to be written
+ * @sc_iput_queue: list of inodes for which iput should be done
+ * @sc_iput_work: work struct to defer iput call
+ * @sc_freesegs: array of segment numbers to be freed
+ * @sc_nfreesegs: number of segments on @sc_freesegs
+ * @sc_dsync_inode: inode whose data pages are written for a sync operation
+ * @sc_dsync_start: start byte offset of data pages
+ * @sc_dsync_end: end byte offset of data pages (inclusive)
+ * @sc_segbufs: List of segment buffers
+ * @sc_write_logs: List of segment buffers to hold logs under writing
+ * @sc_segbuf_nblocks: Number of available blocks in segment buffers.
+ * @sc_curseg: Current segment buffer
+ * @sc_stage: Collection stage
+ * @sc_finfo_ptr: pointer to the current finfo struct in the segment summary
+ * @sc_binfo_ptr: pointer to the current binfo struct in the segment summary
+ * @sc_blk_cnt:	Block count of a file
+ * @sc_datablk_cnt: Data block count of a file
+ * @sc_nblk_this_inc: Number of blocks included in the current logical segment
+ * @sc_seg_ctime: Creation time
+ * @sc_cno: checkpoint number of current log
+ * @sc_flags: Internal flags
+ * @sc_state_lock: spinlock for sc_state and so on
+ * @sc_state: Segctord state flags
+ * @sc_flush_request: inode bitmap of metadata files to be flushed
+ * @sc_wait_request: Client request queue
+ * @sc_wait_daemon: Daemon wait queue
+ * @sc_seq_request: Request counter
+ * @sc_seq_accepted: Accepted request count
+ * @sc_seq_done: Completion counter
+ * @sc_sync: Request of explicit sync operation
+ * @sc_interval: Timeout value of background construction
+ * @sc_mjcp_freq: Frequency of creating checkpoints
+ * @sc_lseg_stime: Start time of the latest logical segment
+ * @sc_watermark: Watermark for the number of dirty buffers
+ * @sc_timer: Timer for segctord
+ * @sc_task: current thread of segctord
+ */
+struct nilfs_sc_info {
+	struct super_block     *sc_super;
+	struct nilfs_root      *sc_root;
+
+	unsigned long		sc_nblk_inc;
+
+	struct list_head	sc_dirty_files;
+	struct list_head	sc_gc_inodes;
+	struct list_head	sc_iput_queue;
+	struct work_struct	sc_iput_work;
+
+	__u64		       *sc_freesegs;
+	size_t			sc_nfreesegs;
+
+	struct nilfs_inode_info *sc_dsync_inode;
+	loff_t			sc_dsync_start;
+	loff_t			sc_dsync_end;
+
+	/* Segment buffers */
+	struct list_head	sc_segbufs;
+	struct list_head	sc_write_logs;
+	unsigned long		sc_segbuf_nblocks;
+	struct nilfs_segment_buffer *sc_curseg;
+
+	struct nilfs_cstage	sc_stage;
+
+	struct nilfs_segsum_pointer sc_finfo_ptr;
+	struct nilfs_segsum_pointer sc_binfo_ptr;
+	unsigned long		sc_blk_cnt;
+	unsigned long		sc_datablk_cnt;
+	unsigned long		sc_nblk_this_inc;
+	time64_t		sc_seg_ctime;
+	__u64			sc_cno;
+	unsigned long		sc_flags;
+
+	spinlock_t		sc_state_lock;
+	unsigned long		sc_state;
+	unsigned long		sc_flush_request;
+
+	wait_queue_head_t	sc_wait_request;
+	wait_queue_head_t	sc_wait_daemon;
+
+	__u32			sc_seq_request;
+	__u32			sc_seq_accepted;
+	__u32			sc_seq_done;
+
+	int			sc_sync;
+	unsigned long		sc_interval;
+	unsigned long		sc_mjcp_freq;
+	unsigned long		sc_lseg_stime;	/* in 1/HZ seconds */
+	unsigned long		sc_watermark;
+
+	struct timer_list	sc_timer;
+	struct task_struct     *sc_task;
+};
+
+/* sc_flags */
+enum {
+	NILFS_SC_DIRTY,		/* One or more dirty meta-data blocks exist */
+	NILFS_SC_UNCLOSED,	/* Logical segment is not closed */
+	NILFS_SC_SUPER_ROOT,	/* The latest segment has a super root */
+	NILFS_SC_PRIOR_FLUSH,	/*
+				 * Requesting immediate flush without making a
+				 * checkpoint
+				 */
+	NILFS_SC_HAVE_DELTA,	/*
+				 * Next checkpoint will have update of files
+				 * other than DAT, cpfile, sufile, or files
+				 * moved by GC.
+				 */
+};
+
+/* sc_state */
+#define NILFS_SEGCTOR_COMMIT	    0x0004  /* committed transaction exists */
+
+/*
+ * Constant parameters
+ */
+#define NILFS_SC_CLEANUP_RETRY	    3  /*
+					* Retry count of construction when
+					* destroying segctord
+					*/
+
+/*
+ * Default values of timeout, in seconds.
+ */
+#define NILFS_SC_DEFAULT_TIMEOUT    5   /*
+					 * Timeout value of dirty blocks.
+					 * It triggers construction of a
+					 * logical segment with a super root.
+					 */
+#define NILFS_SC_DEFAULT_SR_FREQ    30  /*
+					 * Maximum frequency of super root
+					 * creation
+					 */
+
+/*
+ * The default threshold amount of data, in block counts.
+ */
+#define NILFS_SC_DEFAULT_WATERMARK  3600
+
+/* super.c */
+extern struct kmem_cache *nilfs_transaction_cachep;
+
+/* segment.c */
+extern void nilfs_relax_pressure_in_lock(struct super_block *);
+
+extern int nilfs_construct_segment(struct super_block *);
+extern int nilfs_construct_dsync_segment(struct super_block *, struct inode *,
+					 loff_t, loff_t);
+extern int nilfs_clean_segments(struct super_block *, struct nilfs_argv *,
+				void **);
+
+int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root);
+void nilfs_detach_log_writer(struct super_block *sb);
+
+/* recovery.c */
+extern int nilfs_read_super_root_block(struct the_nilfs *, sector_t,
+				       struct buffer_head **, int);
+extern int nilfs_search_super_root(struct the_nilfs *,
+				   struct nilfs_recovery_info *);
+int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, struct super_block *sb,
+			      struct nilfs_recovery_info *ri);
+extern void nilfs_dispose_segment_list(struct list_head *);
+
+#endif /* _NILFS_SEGMENT_H */