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, 221 insertions, 0 deletions

diff --git a/block/elevator.h b/block/elevator.h
new file mode 100644
index 000000000..3eb32516b
--- /dev/null
+++ b/block/elevator.h
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ELEVATOR_H
+#define _ELEVATOR_H
+
+#include <linux/percpu.h>
+#include <linux/hashtable.h>
+#include "blk-mq.h"
+
+struct io_cq;
+struct elevator_type;
+struct blk_mq_debugfs_attr;
+
+/*
+ * Return values from elevator merger
+ */
+enum elv_merge {
+	ELEVATOR_NO_MERGE	= 0,
+	ELEVATOR_FRONT_MERGE	= 1,
+	ELEVATOR_BACK_MERGE	= 2,
+	ELEVATOR_DISCARD_MERGE	= 3,
+};
+
+struct blk_mq_alloc_data;
+struct blk_mq_hw_ctx;
+
+struct elevator_tags {
+	/* num. of hardware queues for which tags are allocated */
+	unsigned int nr_hw_queues;
+	/* depth used while allocating tags */
+	unsigned int nr_requests;
+	/* shared tag is stored at index 0 */
+	struct blk_mq_tags *tags[];
+};
+
+struct elevator_resources {
+	/* holds elevator data */
+	void *data;
+	/* holds elevator tags */
+	struct elevator_tags *et;
+};
+
+/* Holding context data for changing elevator */
+struct elv_change_ctx {
+	const char *name;
+	bool no_uevent;
+
+	/* for unregistering old elevator */
+	struct elevator_queue *old;
+	/* for registering new elevator */
+	struct elevator_queue *new;
+	/* store elevator type */
+	struct elevator_type *type;
+	/* store elevator resources */
+	struct elevator_resources res;
+};
+
+struct elevator_mq_ops {
+	int (*init_sched)(struct request_queue *, struct elevator_queue *);
+	void (*exit_sched)(struct elevator_queue *);
+	int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
+	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
+	void (*depth_updated)(struct request_queue *);
+	void *(*alloc_sched_data)(struct request_queue *);
+	void (*free_sched_data)(void *);
+
+	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
+	bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int);
+	int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
+	void (*request_merged)(struct request_queue *, struct request *, enum elv_merge);
+	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
+	void (*limit_depth)(blk_opf_t, struct blk_mq_alloc_data *);
+	void (*prepare_request)(struct request *);
+	void (*finish_request)(struct request *);
+	void (*insert_requests)(struct blk_mq_hw_ctx *hctx, struct list_head *list,
+			blk_insert_t flags);
+	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
+	bool (*has_work)(struct blk_mq_hw_ctx *);
+	void (*completed_request)(struct request *, u64);
+	void (*requeue_request)(struct request *);
+	struct request *(*former_request)(struct request_queue *, struct request *);
+	struct request *(*next_request)(struct request_queue *, struct request *);
+	void (*init_icq)(struct io_cq *);
+	void (*exit_icq)(struct io_cq *);
+};
+
+#define ELV_NAME_MAX	(16)
+
+struct elv_fs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct elevator_queue *, char *);
+	ssize_t (*store)(struct elevator_queue *, const char *, size_t);
+};
+
+/*
+ * identifies an elevator type, such as AS or deadline
+ */
+struct elevator_type
+{
+	/* managed by elevator core */
+	struct kmem_cache *icq_cache;
+
+	/* fields provided by elevator implementation */
+	struct elevator_mq_ops ops;
+
+	size_t icq_size;	/* see iocontext.h */
+	size_t icq_align;	/* ditto */
+	const struct elv_fs_entry *elevator_attrs;
+	const char *elevator_name;
+	const char *elevator_alias;
+	struct module *elevator_owner;
+#ifdef CONFIG_BLK_DEBUG_FS
+	const struct blk_mq_debugfs_attr *queue_debugfs_attrs;
+	const struct blk_mq_debugfs_attr *hctx_debugfs_attrs;
+#endif
+
+	/* managed by elevator core */
+	char icq_cache_name[ELV_NAME_MAX + 6];	/* elvname + "_io_cq" */
+	struct list_head list;
+};
+
+static inline bool elevator_tryget(struct elevator_type *e)
+{
+	return try_module_get(e->elevator_owner);
+}
+
+static inline void __elevator_get(struct elevator_type *e)
+{
+	__module_get(e->elevator_owner);
+}
+
+static inline void elevator_put(struct elevator_type *e)
+{
+	module_put(e->elevator_owner);
+}
+
+#define ELV_HASH_BITS 6
+
+void elv_rqhash_del(struct request_queue *q, struct request *rq);
+void elv_rqhash_add(struct request_queue *q, struct request *rq);
+void elv_rqhash_reposition(struct request_queue *q, struct request *rq);
+struct request *elv_rqhash_find(struct request_queue *q, sector_t offset);
+
+/*
+ * each queue has an elevator_queue associated with it
+ */
+struct elevator_queue
+{
+	struct elevator_type *type;
+	struct elevator_tags *et;
+	void *elevator_data;
+	struct kobject kobj;
+	struct mutex sysfs_lock;
+	unsigned long flags;
+	DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
+};
+
+#define ELEVATOR_FLAG_REGISTERED	0
+#define ELEVATOR_FLAG_DYING		1
+
+/*
+ * block elevator interface
+ */
+extern enum elv_merge elv_merge(struct request_queue *, struct request **,
+		struct bio *);
+extern void elv_merge_requests(struct request_queue *, struct request *,
+			       struct request *);
+extern void elv_merged_request(struct request_queue *, struct request *,
+		enum elv_merge);
+extern bool elv_attempt_insert_merge(struct request_queue *, struct request *,
+				     struct list_head *);
+extern struct request *elv_former_request(struct request_queue *, struct request *);
+extern struct request *elv_latter_request(struct request_queue *, struct request *);
+
+/*
+ * io scheduler registration
+ */
+extern int elv_register(struct elevator_type *);
+extern void elv_unregister(struct elevator_type *);
+
+/*
+ * io scheduler sysfs switching
+ */
+ssize_t elv_iosched_show(struct gendisk *disk, char *page);
+ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count);
+
+extern bool elv_bio_merge_ok(struct request *, struct bio *);
+struct elevator_queue *elevator_alloc(struct request_queue *,
+		struct elevator_type *, struct elevator_resources *);
+
+/*
+ * Helper functions.
+ */
+extern struct request *elv_rb_former_request(struct request_queue *, struct request *);
+extern struct request *elv_rb_latter_request(struct request_queue *, struct request *);
+
+/*
+ * rb support functions.
+ */
+extern void elv_rb_add(struct rb_root *, struct request *);
+extern void elv_rb_del(struct rb_root *, struct request *);
+extern struct request *elv_rb_find(struct rb_root *, sector_t);
+
+/*
+ * Insertion selection
+ */
+#define ELEVATOR_INSERT_FRONT	1
+#define ELEVATOR_INSERT_BACK	2
+#define ELEVATOR_INSERT_SORT	3
+#define ELEVATOR_INSERT_REQUEUE	4
+#define ELEVATOR_INSERT_FLUSH	5
+#define ELEVATOR_INSERT_SORT_MERGE	6
+
+#define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
+
+#define rq_entry_fifo(ptr)	list_entry((ptr), struct request, queuelist)
+#define rq_fifo_clear(rq)	list_del_init(&(rq)->queuelist)
+
+void blk_mq_sched_reg_debugfs(struct request_queue *q);
+void blk_mq_sched_unreg_debugfs(struct request_queue *q);
+
+#endif /* _ELEVATOR_H */