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, 255 insertions, 0 deletions

diff --git a/drivers/md/dm.h b/drivers/md/dm.h
new file mode 100644
index 000000000..7a795979e
--- /dev/null
+++ b/drivers/md/dm.h
@@ -0,0 +1,255 @@
+/*
+ * Internal header file for device mapper
+ *
+ * Copyright (C) 2001, 2002 Sistina Software
+ * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#ifndef DM_INTERNAL_H
+#define DM_INTERNAL_H
+
+#include <linux/fs.h>
+#include <linux/device-mapper.h>
+#include <linux/list.h>
+#include <linux/moduleparam.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/hdreg.h>
+#include <linux/completion.h>
+#include <linux/kobject.h>
+#include <linux/refcount.h>
+#include <linux/log2.h>
+
+#include "dm-stats.h"
+
+/*
+ * Suspend feature flags
+ */
+#define DM_SUSPEND_LOCKFS_FLAG		(1 << 0)
+#define DM_SUSPEND_NOFLUSH_FLAG		(1 << 1)
+
+/*
+ * Status feature flags
+ */
+#define DM_STATUS_NOFLUSH_FLAG		(1 << 0)
+
+/*
+ * List of devices that a metadevice uses and should open/close.
+ */
+struct dm_dev_internal {
+	struct list_head list;
+	refcount_t count;
+	struct dm_dev *dm_dev;
+};
+
+struct dm_table;
+struct dm_md_mempools;
+struct dm_target_io;
+struct dm_io;
+
+/*
+ *---------------------------------------------------------------
+ * Internal table functions.
+ *---------------------------------------------------------------
+ */
+void dm_table_event_callback(struct dm_table *t,
+			     void (*fn)(void *), void *context);
+struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector);
+bool dm_table_has_no_data_devices(struct dm_table *table);
+bool dm_table_is_wildcard(struct dm_table *t);
+int dm_calculate_queue_limits(struct dm_table *table,
+			      struct queue_limits *limits);
+int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
+			      struct queue_limits *limits);
+struct list_head *dm_table_get_devices(struct dm_table *t);
+void dm_table_presuspend_targets(struct dm_table *t);
+void dm_table_presuspend_undo_targets(struct dm_table *t);
+void dm_table_postsuspend_targets(struct dm_table *t);
+int dm_table_resume_targets(struct dm_table *t);
+enum dm_queue_mode dm_table_get_type(struct dm_table *t);
+struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
+struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
+struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
+bool dm_table_request_based(struct dm_table *t);
+bool dm_table_supports_size_change(struct dm_table *t, sector_t old_size,
+				   sector_t new_size);
+
+void dm_lock_md_type(struct mapped_device *md);
+void dm_unlock_md_type(struct mapped_device *md);
+enum dm_queue_mode dm_get_md_type(struct mapped_device *md);
+struct target_type *dm_get_immutable_target_type(struct mapped_device *md);
+
+int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
+
+/*
+ * To check whether the target type is bio-based or not (request-based).
+ */
+#define dm_target_bio_based(t) ((t)->type->map != NULL)
+
+/*
+ * To check whether the target type is request-based or not (bio-based).
+ */
+#define dm_target_request_based(t) ((t)->type->clone_and_map_rq != NULL)
+
+/*
+ * To check whether the target type is a hybrid (capable of being
+ * either request-based or bio-based).
+ */
+#define dm_target_hybrid(t) (dm_target_bio_based(t) && dm_target_request_based(t))
+
+/*
+ * Zoned targets related functions.
+ */
+int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+		struct queue_limits *lim);
+int dm_revalidate_zones(struct dm_table *t, struct request_queue *q);
+void dm_finalize_zone_settings(struct dm_table *t, struct queue_limits *lim);
+void dm_zone_endio(struct dm_io *io, struct bio *clone);
+#ifdef CONFIG_BLK_DEV_ZONED
+int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
+			unsigned int nr_zones,
+			struct blk_report_zones_args *args);
+bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
+int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t,
+			     sector_t sector, unsigned int nr_zones,
+			     unsigned long *need_reset);
+#define dm_has_zone_plugs(md) ((md)->disk->zone_wplugs_hash != NULL)
+#else
+#define dm_blk_report_zones	NULL
+static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
+{
+	return false;
+}
+#define dm_has_zone_plugs(md) false
+#endif
+
+/*
+ *---------------------------------------------------------------
+ * A registry of target types.
+ *---------------------------------------------------------------
+ */
+int dm_target_init(void);
+void dm_target_exit(void);
+struct target_type *dm_get_target_type(const char *name);
+void dm_put_target_type(struct target_type *tt);
+int dm_target_iterate(void (*iter_func)(struct target_type *tt,
+					void *param), void *param);
+
+int dm_split_args(int *argc, char ***argvp, char *input);
+
+/*
+ * Is this mapped_device being deleted?
+ */
+int dm_deleting_md(struct mapped_device *md);
+
+/*
+ * Is this mapped_device suspended?
+ */
+int dm_suspended_md(struct mapped_device *md);
+
+/*
+ * Internal suspend and resume methods.
+ */
+int dm_suspended_internally_md(struct mapped_device *md);
+void dm_internal_suspend_fast(struct mapped_device *md);
+void dm_internal_resume_fast(struct mapped_device *md);
+void dm_internal_suspend_noflush(struct mapped_device *md);
+void dm_internal_resume(struct mapped_device *md);
+
+/*
+ * Test if the device is scheduled for deferred remove.
+ */
+int dm_test_deferred_remove_flag(struct mapped_device *md);
+
+/*
+ * Try to remove devices marked for deferred removal.
+ */
+void dm_deferred_remove(void);
+
+/*
+ * The device-mapper can be driven through one of two interfaces;
+ * ioctl or filesystem, depending which patch you have applied.
+ */
+int dm_interface_init(void);
+void dm_interface_exit(void);
+
+/*
+ * sysfs interface
+ */
+int dm_sysfs_init(struct mapped_device *md);
+void dm_sysfs_exit(struct mapped_device *md);
+struct kobject *dm_kobject(struct mapped_device *md);
+struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
+
+/*
+ * The kobject helper
+ */
+void dm_kobject_release(struct kobject *kobj);
+
+/*
+ * Targets for linear and striped mappings
+ */
+int linear_map(struct dm_target *ti, struct bio *bio);
+int dm_linear_init(void);
+void dm_linear_exit(void);
+
+int stripe_map(struct dm_target *ti, struct bio *bio);
+int dm_stripe_init(void);
+void dm_stripe_exit(void);
+
+/*
+ * mapped_device operations
+ */
+void dm_destroy(struct mapped_device *md);
+void dm_destroy_immediate(struct mapped_device *md);
+int dm_open_count(struct mapped_device *md);
+int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred);
+int dm_cancel_deferred_remove(struct mapped_device *md);
+int dm_request_based(struct mapped_device *md);
+int dm_get_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode,
+			struct dm_dev **result);
+void dm_put_table_device(struct mapped_device *md, struct dm_dev *d);
+
+int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
+		      unsigned int cookie, bool need_resize_uevent);
+
+int dm_io_init(void);
+void dm_io_exit(void);
+
+int dm_kcopyd_init(void);
+void dm_kcopyd_exit(void);
+
+/*
+ * Mempool operations
+ */
+void dm_free_md_mempools(struct dm_md_mempools *pools);
+
+/*
+ * Various helpers
+ */
+unsigned int dm_get_reserved_bio_based_ios(void);
+
+#define DM_HASH_LOCKS_MAX 64
+
+static inline unsigned int dm_num_hash_locks(void)
+{
+	unsigned int num_locks = roundup_pow_of_two(num_online_cpus()) << 1;
+
+	return min_t(unsigned int, num_locks, DM_HASH_LOCKS_MAX);
+}
+
+#define DM_HASH_LOCKS_MULT  4294967291ULL
+#define DM_HASH_LOCKS_SHIFT 6
+
+static inline unsigned int dm_hash_locks_index(sector_t block,
+					       unsigned int num_locks)
+{
+	sector_t h1 = (block * DM_HASH_LOCKS_MULT) >> DM_HASH_LOCKS_SHIFT;
+	sector_t h2 = h1 >> DM_HASH_LOCKS_SHIFT;
+
+	return (h1 ^ h2) & (num_locks - 1);
+}
+
+#endif