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, 173 insertions, 0 deletions

diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
new file mode 100644
index 000000000..07bd838e7
--- /dev/null
+++ b/fs/ocfs2/inode.h
@@ -0,0 +1,173 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * inode.h
+ *
+ * Function prototypes
+ *
+ * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
+ */
+
+#ifndef OCFS2_INODE_H
+#define OCFS2_INODE_H
+
+#include "extent_map.h"
+
+/* OCFS2 Inode Private Data */
+struct ocfs2_inode_info
+{
+	u64			ip_blkno;
+
+	struct ocfs2_lock_res		ip_rw_lockres;
+	struct ocfs2_lock_res		ip_inode_lockres;
+	struct ocfs2_lock_res		ip_open_lockres;
+
+	/* protects allocation changes on this inode. */
+	struct rw_semaphore		ip_alloc_sem;
+
+	/* protects extended attribute changes on this inode */
+	struct rw_semaphore		ip_xattr_sem;
+
+	/* These fields are protected by ip_lock */
+	spinlock_t			ip_lock;
+	u32				ip_open_count;
+	struct list_head		ip_io_markers;
+	u32				ip_clusters;
+
+	u16				ip_dyn_features;
+	struct mutex			ip_io_mutex;
+	u32				ip_flags; /* see below */
+	u32				ip_attr; /* inode attributes */
+
+	/* Record unwritten extents during direct io. */
+	struct list_head		ip_unwritten_list;
+
+	/* protected by recovery_lock. */
+	struct inode			*ip_next_orphan;
+
+	struct ocfs2_caching_info	ip_metadata_cache;
+	struct ocfs2_extent_map		ip_extent_map;
+	struct inode			vfs_inode;
+	struct jbd2_inode		ip_jinode;
+
+	u32				ip_dir_start_lookup;
+
+	/* Only valid if the inode is the dir. */
+	u32				ip_last_used_slot;
+	u64				ip_last_used_group;
+	u32				ip_dir_lock_gen;
+
+	struct ocfs2_alloc_reservation	ip_la_data_resv;
+
+	/*
+	 * Transactions that contain inode's metadata needed to complete
+	 * fsync and fdatasync, respectively.
+	 */
+	tid_t i_sync_tid;
+	tid_t i_datasync_tid;
+
+	struct dquot __rcu *i_dquot[MAXQUOTAS];
+};
+
+/*
+ * Flags for the ip_flags field
+ */
+/* System file inodes  */
+#define OCFS2_INODE_SYSTEM_FILE		0x00000001
+#define OCFS2_INODE_JOURNAL		0x00000002
+#define OCFS2_INODE_BITMAP		0x00000004
+/* This inode has been wiped from disk */
+#define OCFS2_INODE_DELETED		0x00000008
+/* Has the inode been orphaned on another node?
+ *
+ * This hints to ocfs2_drop_inode that it should clear i_nlink before
+ * continuing.
+ *
+ * We *only* set this on unlink vote from another node. If the inode
+ * was locally orphaned, then we're sure of the state and don't need
+ * to twiddle i_nlink later - it's either zero or not depending on
+ * whether our unlink succeeded. Otherwise we got this from a node
+ * whose intention was to orphan the inode, however he may have
+ * crashed, failed etc, so we let ocfs2_drop_inode zero the value and
+ * rely on ocfs2_delete_inode to sort things out under the proper
+ * cluster locks.
+ */
+#define OCFS2_INODE_MAYBE_ORPHANED	0x00000010
+/* Does someone have the file open O_DIRECT */
+#define OCFS2_INODE_OPEN_DIRECT		0x00000020
+/* Tell the inode wipe code it's not in orphan dir */
+#define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000040
+/* Entry in orphan dir with 'dio-' prefix */
+#define OCFS2_INODE_DIO_ORPHAN_ENTRY	0x00000080
+
+static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode)
+{
+	return container_of(inode, struct ocfs2_inode_info, vfs_inode);
+}
+
+#define INODE_JOURNAL(i) (OCFS2_I(i)->ip_flags & OCFS2_INODE_JOURNAL)
+#define SET_INODE_JOURNAL(i) (OCFS2_I(i)->ip_flags |= OCFS2_INODE_JOURNAL)
+
+extern const struct address_space_operations ocfs2_aops;
+extern const struct ocfs2_caching_operations ocfs2_inode_caching_ops;
+
+static inline struct ocfs2_caching_info *INODE_CACHE(struct inode *inode)
+{
+	return &OCFS2_I(inode)->ip_metadata_cache;
+}
+
+void ocfs2_evict_inode(struct inode *inode);
+
+/* Flags for ocfs2_iget() */
+#define OCFS2_FI_FLAG_SYSFILE		0x1
+#define OCFS2_FI_FLAG_ORPHAN_RECOVERY	0x2
+#define OCFS2_FI_FLAG_FILECHECK_CHK	0x4
+#define OCFS2_FI_FLAG_FILECHECK_FIX	0x8
+
+struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff);
+struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
+			 int sysfile_type);
+int ocfs2_inode_revalidate(struct dentry *dentry);
+void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
+			  int create_ino);
+void ocfs2_sync_blockdev(struct super_block *sb);
+void ocfs2_refresh_inode(struct inode *inode,
+			 struct ocfs2_dinode *fe);
+int ocfs2_mark_inode_dirty(handle_t *handle,
+			   struct inode *inode,
+			   struct buffer_head *bh);
+
+void ocfs2_set_inode_flags(struct inode *inode);
+void ocfs2_get_inode_flags(struct ocfs2_inode_info *oi);
+
+static inline blkcnt_t ocfs2_inode_sector_count(struct inode *inode)
+{
+	int c_to_s_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits - 9;
+
+	return (blkcnt_t)OCFS2_I(inode)->ip_clusters << c_to_s_bits;
+}
+
+/* Validate that a bh contains a valid inode */
+int ocfs2_validate_inode_block(struct super_block *sb,
+			       struct buffer_head *bh);
+/*
+ * Read an inode block into *bh.  If *bh is NULL, a bh will be allocated.
+ * This is a cached read.  The inode will be validated with
+ * ocfs2_validate_inode_block().
+ */
+int ocfs2_read_inode_block(struct inode *inode, struct buffer_head **bh);
+/* The same, but can be passed OCFS2_BH_* flags */
+int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh,
+				int flags);
+
+static inline struct ocfs2_inode_info *cache_info_to_inode(struct ocfs2_caching_info *ci)
+{
+	return container_of(ci, struct ocfs2_inode_info, ip_metadata_cache);
+}
+
+/* Does this inode have the reflink flag set? */
+static inline bool ocfs2_is_refcount_inode(struct inode *inode)
+{
+	return (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL);
+}
+
+#endif /* OCFS2_INODE_H */