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, 115 insertions, 0 deletions

diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h
new file mode 100644
index 000000000..9e23bab3f
--- /dev/null
+++ b/fs/nilfs2/mdt.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * NILFS meta data file prototype and definitions
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * Written by Ryusuke Konishi.
+ */
+
+#ifndef _NILFS_MDT_H
+#define _NILFS_MDT_H
+
+#include <linux/buffer_head.h>
+#include <linux/blockgroup_lock.h>
+#include "nilfs.h"
+#include "page.h"
+
+/**
+ * struct nilfs_shadow_map - shadow mapping of meta data file
+ * @bmap_store: shadow copy of bmap state
+ * @inode: holder of page caches used in shadow mapping
+ * @frozen_buffers: list of frozen buffers
+ */
+struct nilfs_shadow_map {
+	struct nilfs_bmap_store bmap_store;
+	struct inode *inode;
+	struct list_head frozen_buffers;
+};
+
+/**
+ * struct nilfs_mdt_info - on-memory private data of meta data files
+ * @mi_sem: reader/writer semaphore for meta data operations
+ * @mi_bgl: per-blockgroup locking
+ * @mi_entry_size: size of an entry
+ * @mi_first_entry_offset: offset to the first entry
+ * @mi_entries_per_block: number of entries in a block
+ * @mi_palloc_cache: persistent object allocator cache
+ * @mi_shadow: shadow of bmap and page caches
+ * @mi_blocks_per_group: number of blocks in a group
+ * @mi_blocks_per_desc_block: number of blocks per descriptor block
+ */
+struct nilfs_mdt_info {
+	struct rw_semaphore	mi_sem;
+	struct blockgroup_lock *mi_bgl;
+	unsigned int		mi_entry_size;
+	unsigned int		mi_first_entry_offset;
+	unsigned long		mi_entries_per_block;
+	struct nilfs_palloc_cache *mi_palloc_cache;
+	struct nilfs_shadow_map *mi_shadow;
+	unsigned long		mi_blocks_per_group;
+	unsigned long		mi_blocks_per_desc_block;
+};
+
+static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode)
+{
+	return inode->i_private;
+}
+
+static inline int nilfs_is_metadata_file_inode(const struct inode *inode)
+{
+	return inode->i_private != NULL;
+}
+
+/* Default GFP flags using highmem */
+#define NILFS_MDT_GFP      (__GFP_RECLAIM | __GFP_IO | __GFP_HIGHMEM)
+
+int nilfs_mdt_get_block(struct inode *, unsigned long, int,
+			void (*init_block)(struct inode *,
+					   struct buffer_head *, void *),
+			struct buffer_head **);
+int nilfs_mdt_find_block(struct inode *inode, unsigned long start,
+			 unsigned long end, unsigned long *blkoff,
+			 struct buffer_head **out_bh);
+int nilfs_mdt_delete_block(struct inode *, unsigned long);
+int nilfs_mdt_forget_block(struct inode *, unsigned long);
+int nilfs_mdt_fetch_dirty(struct inode *);
+
+int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz);
+void nilfs_mdt_clear(struct inode *inode);
+void nilfs_mdt_destroy(struct inode *inode);
+
+void nilfs_mdt_set_entry_size(struct inode *, unsigned int, unsigned int);
+
+int nilfs_mdt_setup_shadow_map(struct inode *inode,
+			       struct nilfs_shadow_map *shadow);
+int nilfs_mdt_save_to_shadow_map(struct inode *inode);
+void nilfs_mdt_restore_from_shadow_map(struct inode *inode);
+void nilfs_mdt_clear_shadow_map(struct inode *inode);
+int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh);
+struct buffer_head *nilfs_mdt_get_frozen_buffer(struct inode *inode,
+						struct buffer_head *bh);
+
+static inline void nilfs_mdt_mark_dirty(struct inode *inode)
+{
+	if (!test_bit(NILFS_I_DIRTY, &NILFS_I(inode)->i_state))
+		set_bit(NILFS_I_DIRTY, &NILFS_I(inode)->i_state);
+}
+
+static inline void nilfs_mdt_clear_dirty(struct inode *inode)
+{
+	clear_bit(NILFS_I_DIRTY, &NILFS_I(inode)->i_state);
+}
+
+static inline __u64 nilfs_mdt_cno(struct inode *inode)
+{
+	return ((struct the_nilfs *)inode->i_sb->s_fs_info)->ns_cno;
+}
+
+static inline spinlock_t *
+nilfs_mdt_bgl_lock(struct inode *inode, unsigned int block_group)
+{
+	return bgl_lock_ptr(NILFS_MDT(inode)->mi_bgl, block_group);
+}
+
+#endif /* _NILFS_MDT_H */