block: fix blktrace debugfs use after free

index 5847993738f1..e438c3b0815b 100644
@@ -321,6 +321,13 @@ void blk_clear_pm_only(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_clear_pm_only);
 
+/**
+ * blk_put_queue - decrement the request_queue refcount
+ * @q: the request_queue structure to decrement the refcount for
+ *
+ * Decrements the refcount of the request_queue kobject. When this reaches 0
+ * we'll have blk_release_queue() called.
+ */
 void blk_put_queue(struct request_queue *q)
 {
 	kobject_put(&q->kobj);

@@ -598,6 +605,12 @@ struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id)
 }
 EXPORT_SYMBOL(blk_alloc_queue);
 
+/**
+ * blk_get_queue - increment the request_queue refcount
+ * @q: the request_queue structure to increment the refcount for
+ *
+ * Increment the refcount of the request_queue kobject.
+ */
 bool blk_get_queue(struct request_queue *q)
 {
 	if (likely(!blk_queue_dying(q))) {

80 lines not on this page · raw message

index e438c3b0815b..94216fa16a05 100644
@@ -610,6 +610,8 @@ EXPORT_SYMBOL(blk_alloc_queue);
  * @q: the request_queue structure to increment the refcount for
  *
  * Increment the refcount of the request_queue kobject.
+ *
+ * Context: Any context.
  */
 bool blk_get_queue(struct request_queue *q)
 {

index af910e6a0233..598bd32ad28c 100644
@@ -1017,11 +1017,15 @@ static ssize_t disk_badblocks_store(struct device *dev,
  *
  * This function gets the structure containing partitioning
  * information for the given device @devt.
+ *
+ * Context: can sleep
  */
 struct gendisk *get_gendisk(dev_t devt, int *partno)
 {
 	struct gendisk *disk = NULL;
 
+	might_sleep();
+
 	if (MAJOR(devt) != BLOCK_EXT_MAJOR) {
 		struct kobject *kobj;
 

@@ -1785,6 +1789,8 @@ EXPORT_SYMBOL(__alloc_disk_node);
  *
  * This increments the refcount for the struct gendisk, and the gendisk's
  * fops module owner.
+ *
+ * Context: Any context.
  */
 struct kobject *get_disk_and_module(struct gendisk *disk)
 {

index 94216fa16a05..8a785d16033b 100644
@@ -327,6 +327,9 @@ EXPORT_SYMBOL_GPL(blk_clear_pm_only);
  *
  * Decrements the refcount of the request_queue kobject. When this reaches 0
  * we'll have blk_release_queue() called.
+ *
+ * Context: Any context, but the last reference must not be dropped from
+ *          atomic context.
  */
 void blk_put_queue(struct request_queue *q)
 {

@@ -359,9 +362,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying);
  *
  * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and
  * put it.  All future requests will be failed immediately with -ENODEV.
+ *
+ * Context: can sleep
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
+	/* cannot be called from atomic context */
+	might_sleep();
+
 	WARN_ON_ONCE(blk_queue_registered(q));
 
 	/* mark @q DYING, no new request or merges will be allowed afterwards */

59 lines not on this page · raw message

index 598bd32ad28c..ea6abfadb7f5 100644
@@ -921,12 +921,19 @@ static void invalidate_partition(struct gendisk *disk, int partno)
  * The final removal of the struct gendisk happens when its refcount reaches 0
  * with put_disk(), which should be called after del_gendisk(), if
  * __device_add_disk() was used.
+ *
+ * Drivers exist which depend on the release of the gendisk to be synchronous,
+ * it should not be deferred.
+ *
+ * Context: can sleep
  */
 void del_gendisk(struct gendisk *disk)
 {
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
+	might_sleep();
+
 	blk_integrity_del(disk);
 	disk_del_events(disk);
 

@@ -1573,11 +1580,15 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
  * drivers we also call blk_put_queue() for them, and we expect the
  * request_queue refcount to reach 0 at this point, and so the request_queue
  * will also be freed prior to the disk.
+ *
+ * Context: can sleep
  */
 static void disk_release(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	might_sleep();
+
 	blk_free_devt(dev->devt);
 	disk_release_events(disk);
 	kfree(disk->random);

@@ -1818,6 +1829,9 @@ EXPORT_SYMBOL(get_disk_and_module);
  *
  * This decrements the refcount for the struct gendisk. When this reaches 0
  * we'll have disk_release() called.
+ *
+ * Context: Any context, but the last reference must not be dropped from
+ *          atomic context.
  */
 void put_disk(struct gendisk *disk)
 {

@@ -1832,6 +1846,9 @@ EXPORT_SYMBOL(put_disk);
  *
  * This is a counterpart of get_disk_and_module() and thus also of
  * get_gendisk().
+ *
+ * Context: Any context, but the last reference must not be dropped from
+ *          atomic context.
  */
 void put_disk_and_module(struct gendisk *disk)
 {

index 2b33166b9daf..8801f3d7cf4a 100644
@@ -584,8 +584,6 @@ struct request_queue {
 
 	size_t			cmd_size;
 
-	struct work_struct	release_work;
-
 #define BLK_MAX_WRITE_HINTS	5
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };

index 8a785d16033b..d40648958767 100644
@@ -51,10 +51,6 @@
 #include "blk-pm.h"
 #include "blk-rq-qos.h"
 
-#ifdef CONFIG_DEBUG_FS
-struct dentry *blk_debugfs_root;
-#endif
-
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);

@@ -1880,10 +1876,7 @@ int __init blk_dev_init(void)
 
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
-
-#ifdef CONFIG_DEBUG_FS
-	blk_debugfs_root = debugfs_create_dir("block", NULL);
-#endif
+	blk_debugfs_register();
 
 	return 0;
 }

new file mode 100644
index 000000000000..19091e1effc0
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Shared request-based / make_request-based functionality
+ */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/debugfs.h>
+
+struct dentry *blk_debugfs_root;
+
+void blk_debugfs_register(void)
+{
+	blk_debugfs_root = debugfs_create_dir("block", NULL);
+}

index fc00537026a0..ee309233f95e 100644
@@ -458,4 +458,12 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page);
 
+#ifdef CONFIG_DEBUG_FS
+void blk_debugfs_register(void);
+#else
+static inline void blk_debugfs_register(void)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
 #endif /* BLK_INTERNAL_H */

index 19091e1effc0..8121f297eaba 100644
@@ -8,8 +8,190 @@
 #include <linux/debugfs.h>
 
 struct dentry *blk_debugfs_root;
+struct dentry *blk_debugfs_bsg = NULL;
+
+/**
+ * enum blk_debugfs_dir_type - block device debugfs directory type
+ * @BLK_DBG_DIR_BASE: the block device debugfs_dir exists on the base
+ * 	system <system-debugfs-dir>/block/ debugfs directory.
+ * @BLK_DBG_DIR_BSG: the block device debugfs_dir is under the directory
+ * 	<system-debugfs-dir>/block/bsg/
+ */
+enum blk_debugfs_dir_type {
+	BLK_DBG_DIR_BASE = 1,
+	BLK_DBG_DIR_BSG,
+};
 
 void blk_debugfs_register(void)
 {
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
 }
+
+static struct dentry *queue_get_base_dir(enum blk_debugfs_dir_type type)
+{
+	switch (type) {
+	case BLK_DBG_DIR_BASE:
+		return blk_debugfs_root;
+	case BLK_DBG_DIR_BSG:
+		return blk_debugfs_bsg;
+	}
+	return NULL;
+}
+
+static void queue_debugfs_register_type(struct request_queue *q,
+					const char *name,
+					enum blk_debugfs_dir_type type)
+{
+	struct dentry *base_dir = queue_get_base_dir(type);
+
+	q->debugfs_dir = debugfs_create_dir(name, base_dir);
+}
+
+/**
+ * blk_queue_debugfs_register - register the debugfs_dir for the block device
+ * @q: the associated request_queue of the block device
+ * @name: the name of the block device exposed
+ *
+ * This is used to create the debugfs_dir used by the block layer and blktrace.
+ * Drivers which use any of the *add_disk*() calls or variants have this called
+ * automatically for them. This directory is removed automatically on
+ * blk_release_queue() once the request_queue reference count reaches 0.
+ */
+void blk_queue_debugfs_register(struct request_queue *q, const char *name)
+{
+	queue_debugfs_register_type(q, name, BLK_DBG_DIR_BASE);
+}
+EXPORT_SYMBOL_GPL(blk_queue_debugfs_register);
+
+/**
+ * blk_queue_debugfs_unregister - remove the debugfs_dir for the block device
+ * @q: the associated request_queue of the block device
+ *
+ * Removes the debugfs_dir for the request_queue on the associated block device.
+ * This is handled for you on blk_release_queue(), and that should only be
+ * called once.
+ *
+ * Since we don't care where the debugfs_dir was created this is used for all
+ * types of of enum blk_debugfs_dir_type.
+ */
+void blk_queue_debugfs_unregister(struct request_queue *q)
+{
+	debugfs_remove_recursive(q->debugfs_dir);
+}
+
+static struct dentry *queue_debugfs_symlink_type(struct request_queue *q,
+						 const char *src,
+						 const char *dst,
+						 enum blk_debugfs_dir_type type)
+{
+	struct dentry *dentry = ERR_PTR(-EINVAL);
+	char *dir_dst = NULL;
+
+	switch (type) {
+	case BLK_DBG_DIR_BASE:
+		if (dst)
+			dir_dst = kasprintf(GFP_KERNEL, "%s", dst);
+		else if (!IS_ERR_OR_NULL(q->debugfs_dir))
+			dir_dst = kasprintf(GFP_KERNEL, "%s",
+					    q->debugfs_dir->d_name.name);
+		else
+			goto out;
+		break;
+	case BLK_DBG_DIR_BSG:
+		if (dst)
+			dir_dst = kasprintf(GFP_KERNEL, "bsg/%s", dst);
+		else
+			goto out;
+		break;
+	}
+
+	/*
+	 * The base block debugfs directory is always used for the symlinks,
+	 * their target is what changes.
+	 */
+	dentry = debugfs_create_symlink(src, blk_debugfs_root, dir_dst);
+	kfree(dir_dst);
+out:
+	return dentry;
+}
+
+/**
+ * blk_queue_debugfs_symlink - symlink to the real block device debugfs_dir
+ * @q: the request queue where we know the debugfs_dir exists or will exist
+ *     eventually. Cannot be NULL.
+ * @src: name of the exposed device we wish to associate to the block device
+ * @dst: the name of the directory to which we want to symlink to, may be NULL
+ *	 if you do not know what this may be, but only if your base block device
+ *	 is not bsg. If you set this to NULL, we will have no other option but
+ *	 to look at the request_queue to infer the name, but you must ensure
+ *	 it is already be set, be mindful of asynchronous probes.
+ *
+ * Some devices don't have a request_queue of their own, however, they have an
+ * association to one and have historically supported using the same
+ * debugfs_dir which has been used to represent the whole disk for blktrace
+ * functionality. Such is the case for partitions and for scsi-generic devices.
+ * They share the same request_queue and debugfs_dir as with the whole disk for
+ * blktrace purposes.  This helper allows such association to be made explicit
+ * and enable blktrace functionality for them. scsi-generic devices representing
+ * scsi device such as block, cdrom, tape, media changer register their own
+ * debug_dir already and share the same request_queue as with scsi-generic, as
+ * such the respective scsi-generic debugfs_dir is just a symlink to these
+ * driver's debugfs_dir.
+ *
+ * To remove use debugfs_remove() on the symlink dentry returned by this
+ * function. The block layer will not clean this up for you, you must remove
+ * it yourself in case of device removal.
+ */
+struct dentry *blk_queue_debugfs_symlink(struct request_queue *q,
+					 const char *src,
+					 const char *dst)
+{
+	return queue_debugfs_symlink_type(q, src, dst, BLK_DBG_DIR_BASE);
+}
+EXPORT_SYMBOL_GPL(blk_queue_debugfs_symlink);
+
+#ifdef CONFIG_BLK_DEV_BSG
+
+void blk_debugfs_register_bsg(void)
+{
+	blk_debugfs_bsg = debugfs_create_dir("bsg", blk_debugfs_root);
+}
+
+/**
+ * blk_queue_debugfs_register_bsg - create the debugfs_dir for bsg block devices
+ * @q: the associated request_queue of the block device
+ * @name: the name of the block device exposed
+ *
+ * This is used to create the debugfs_dir used by the Block layer SCSI generic
+ * (bsg) driver. This is to be used only by the scsi-generic driver on behalf
+ * of scsi devices which work as scsi controllers or transports.
+ *
+ * This directory is cleaned up for all drivers automatically on
+ * blk_release_queue() once the request_queue reference count reaches 0.
+ */
+void blk_queue_debugfs_register_bsg(struct request_queue *q, const char *name)
+{
+	queue_debugfs_register_type(q, name, BLK_DBG_DIR_BSG);
+}
+EXPORT_SYMBOL_GPL(blk_queue_debugfs_register_bsg);
+
+/**
+ * blk_queue_debugfs_symlink_bsg - symlink to the bsg debugfs_dir
+ * @q: the request queue where we know the debugfs_dir exists or will exist
+ *     eventually. Cannot be NULL.
+ * @src: name of the scsi-generic device we wish to associate to the bsg
+ * 	request_queue.
+ * @dst: the name of the bsg request_queue debugfs_dir to which we want to
+ *	 symlink to. This cannot be NULL.
+ *
+ * This is used by scsi-generic devices representing raid controllers /
+ * transport drivers.
+ */
+struct dentry *blk_queue_debugfs_bsg_symlink(struct request_queue *q,
+					     const char *src,
+					     const char *dst)
+{
+	return queue_debugfs_symlink_type(q, src, dst, BLK_DBG_DIR_BSG);
+}
+EXPORT_SYMBOL_GPL(blk_queue_debugfs_bsg_symlink);
+#endif /* CONFIG_BLK_DEV_BSG */

index 96b7a35c898a..08edc3a54114 100644
@@ -822,9 +822,6 @@ void blk_mq_debugfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
-					    blk_debugfs_root);
-
 	debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs);
 
 	/*

@@ -855,9 +852,7 @@ void blk_mq_debugfs_register(struct request_queue *q)
 
 void blk_mq_debugfs_unregister(struct request_queue *q)
 {
-	debugfs_remove_recursive(q->debugfs_dir);
 	q->sched_debugfs_dir = NULL;
-	q->debugfs_dir = NULL;
 }
 
 static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,

index 561624d4cc4e..4e0c00a88c99 100644
@@ -918,6 +918,7 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_trace_shutdown(q);
 
+	blk_queue_debugfs_unregister(q);
 	if (queue_is_mq(q))
 		blk_mq_debugfs_unregister(q);
 

@@ -989,6 +990,8 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	blk_queue_debugfs_register(q, kobject_name(q->kobj.parent));
+
 	if (queue_is_mq(q)) {
 		__blk_mq_register_dev(dev, q);
 		blk_mq_debugfs_register(q);

index ee309233f95e..300b8526066b 100644
@@ -460,10 +460,26 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 
 #ifdef CONFIG_DEBUG_FS
 void blk_debugfs_register(void);
+void blk_queue_debugfs_unregister(struct request_queue *q);
+void blk_part_debugfs_register(struct hd_struct *p, const char *name);
+void blk_part_debugfs_unregister(struct hd_struct *p);
 #else
 static inline void blk_debugfs_register(void)
 {
 }
+
+static inline void blk_queue_debugfs_unregister(struct request_queue *q)
+{
+}
+
+static inline void blk_part_debugfs_register(struct hd_struct *p,
+					     const char *name)
+{
+}
+
+static inline void blk_part_debugfs_unregister(struct hd_struct *p)
+{
+}
 #endif /* CONFIG_DEBUG_FS */
 
 #endif /* BLK_INTERNAL_H */

index d7bae94b64d9..bfb1036858c4 100644
@@ -503,6 +503,8 @@ static int __init bsg_init(void)
 	if (ret)
 		goto unregister_chrdev;
 
+	blk_debugfs_register_bsg();
+
 	printk(KERN_INFO BSG_DESCRIPTION " version " BSG_VERSION
 	       " loaded (major %d)\n", bsg_major);
 	return 0;

index 297004fd2264..4d2a130e6055 100644
@@ -10,6 +10,7 @@
 #include <linux/vmalloc.h>
 #include <linux/blktrace_api.h>
 #include <linux/raid/detect.h>
+#include <linux/debugfs.h>
 #include "check.h"
 
 static int (*check_part[])(struct parsed_partitions *) = {

@@ -320,6 +321,9 @@ void delete_partition(struct gendisk *disk, struct hd_struct *part)
 	 *  we have to hold the disk device
 	 */
 	get_device(disk_to_dev(part_to_disk(part)));
+#ifdef CONFIG_DEBUG_FS
+	debugfs_remove(part->debugfs_sym);
+#endif
 	rcu_assign_pointer(ptbl->part[part->partno], NULL);
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));

@@ -460,6 +464,11 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	/* everything is up and running, commence */
 	rcu_assign_pointer(ptbl->part[partno], p);
 
+#ifdef CONFIG_DEBUG_FS
+	p->debugfs_sym = blk_queue_debugfs_symlink(disk->queue, dev_name(pdev),
+						   disk->disk_name);
+#endif
+
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);

index cb74ab1ae5a4..5dfabc04bfef 100644
@@ -971,6 +971,7 @@ static int ch_probe(struct device *dev)
 
 	mutex_unlock(&ch->lock);
 	dev_set_drvdata(dev, ch);
+	blk_queue_debugfs_register(sd->request_queue, dev_name(class_dev));
 	sdev_printk(KERN_INFO, sd, "Attached scsi changer %s\n", ch->name);
 
 	return 0;

105 lines not on this page · raw message

index 4bf4ab3b70f4..fb3c0546803a 100644
@@ -4417,6 +4417,8 @@ static int st_probe(struct device *dev)
 	if (error)
 		goto out_remove_devs;
 	scsi_autopm_put_device(SDp);
+	blk_queue_debugfs_register(tpnt->device->request_queue,
+				   tape_name(tpnt));
 
 	sdev_printk(KERN_NOTICE, SDp,
 		    "Attached scsi tape %s\n", tape_name(tpnt));

index 8801f3d7cf4a..0e6dff9c4233 100644
@@ -574,8 +574,10 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
 
-#ifdef CONFIG_BLK_DEBUG_FS
+#ifdef CONFIG_DEBUG_FS
 	struct dentry		*debugfs_dir;
+#endif
+#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
 #endif

index 3b6ff5902edc..eb6db276e293 100644
@@ -22,7 +22,6 @@ struct blk_trace {
 	u64 end_lba;
 	u32 pid;
 	u32 dev;
-	struct dentry *dir;
 	struct dentry *dropped_file;
 	struct dentry *msg_file;
 	struct list_head running_list;

81 lines not on this page · raw message

index ca39dc3230cb..6c10a1427de2 100644
@@ -311,7 +311,6 @@ static void blk_trace_free(struct blk_trace *bt)
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
 	relay_close(bt->rchan);
-	debugfs_remove(bt->dir);
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);

@@ -509,9 +508,24 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = -ENOENT;
 
-	dir = debugfs_lookup(buts->name, blk_debugfs_root);
-	if (!dir)
-		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
+	dir = q->debugfs_dir;
+
+	/*
+	 * Although the directory here is from debugfs, and we typically do not
+	 * care about NULL dirs as debugfs is typically only used for debugging,
+	 * we rely on the directory to exist to place files which we then use
+	 * for blktrace userspace functionality. Without this directory
+	 * blktrace would not work. Enabling blktrace functionality enables
+	 * debugfs too, as such, we *really* do want to check for this and must
+	 * ensure it was set before chugging on. If NULL were used below, we'd
+	 * also end up creating the debugfs files under the block root
+	 * directory, which we definitely do not want.
+	 */
+	if (IS_ERR_OR_NULL(dir)) {
+		pr_warn("debugfs_dir not present for %s so skipping\n",
+			buts->name);
+		goto err;
+	}
 
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);

@@ -551,8 +565,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = 0;
 err:
-	if (dir && !bt->dir)
-		dput(dir);
 	if (ret)
 		blk_trace_free(bt);
 	return ret;

index 15df3a36e9fa4..a2800bc56fb4d 100644
@@ -824,9 +824,6 @@ void blk_mq_debugfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
-					    blk_debugfs_root);
-
 	debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs);
 
 	/*

@@ -857,9 +854,7 @@ void blk_mq_debugfs_register(struct request_queue *q)
 
 void blk_mq_debugfs_unregister(struct request_queue *q)
 {
-	debugfs_remove_recursive(q->debugfs_dir);
 	q->sched_debugfs_dir = NULL;
-	q->debugfs_dir = NULL;
 }
 
 static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,

index 561624d4cc4e7..8e6ea4a13f550 100644
@@ -11,6 +11,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-cgroup.h>
+#include <linux/debugfs.h>
 
 #include "blk.h"
 #include "blk-mq.h"

@@ -918,6 +919,7 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_trace_shutdown(q);
 
+	debugfs_remove_recursive(q->debugfs_dir);
 	if (queue_is_mq(q))
 		blk_mq_debugfs_unregister(q);
 

@@ -989,6 +991,27 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	/*
+	 * Blktrace needs a debugsfs name even for queues that don't register
+	 * a gendisk, so it lazily registers the debugfs directory.  But that
+	 * can get us into a situation where a SCSI device is found, with no
+	 * driver for it (yet).  Then blktrace is used on the device, creating
+	 * the debugfs directory, and only after that a drivers is loaded. In
+	 * that case we might already have a debugfs directory registered here.
+	 * Even worse we could be racing with blktrace to register it.
+	 */
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	mutex_lock(&q->blk_trace_mutex);
+	if (!q->debugfs_dir) {
+		q->debugfs_dir =
+			debugfs_create_dir(kobject_name(q->kobj.parent),
+				blk_debugfs_root);
+	}
+	mutex_unlock(&q->blk_trace_mutex);
+#else
+	blk_queue_debugfs_register(q);
+#endif
+
 	if (queue_is_mq(q)) {
 		__blk_mq_register_dev(dev, q);
 		blk_mq_debugfs_register(q);

index 8801f3d7cf4a3..7a4de524f408f 100644
@@ -574,8 +574,8 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
 
-#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
+#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
 #endif

index 3b6ff5902edce..eb6db276e2931 100644
@@ -22,7 +22,6 @@ struct blk_trace {
 	u64 end_lba;
 	u32 pid;
 	u32 dev;
-	struct dentry *dir;
 	struct dentry *dropped_file;
 	struct dentry *msg_file;
 	struct list_head running_list;

83 lines not on this page · raw message

index 2096373bd16d..67cd9ddac822 100644
@@ -51,9 +51,7 @@
 #include "blk-pm.h"
 #include "blk-rq-qos.h"
 
-#ifdef CONFIG_DEBUG_FS
 struct dentry *blk_debugfs_root;
-#endif
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);

@@ -1877,9 +1875,7 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
-#ifdef CONFIG_DEBUG_FS
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
-#endif
 
 	return 0;
 }

index 96b7a35c898a..08edc3a54114 100644
@@ -822,9 +822,6 @@ void blk_mq_debugfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
-					    blk_debugfs_root);
-
 	debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs);
 
 	/*

@@ -855,9 +852,7 @@ void blk_mq_debugfs_register(struct request_queue *q)
 
 void blk_mq_debugfs_unregister(struct request_queue *q)
 {
-	debugfs_remove_recursive(q->debugfs_dir);
 	q->sched_debugfs_dir = NULL;
-	q->debugfs_dir = NULL;
 }
 
 static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,

index 561624d4cc4e..5babb6547f48 100644
@@ -11,6 +11,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-cgroup.h>
+#include <linux/debugfs.h>
 
 #include "blk.h"
 #include "blk-mq.h"

@@ -918,6 +919,7 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_trace_shutdown(q);
 
+	debugfs_remove_recursive(q->debugfs_dir);
 	if (queue_is_mq(q))
 		blk_mq_debugfs_unregister(q);
 

@@ -989,6 +991,28 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	/*
+	 * Blktrace needs a debugsfs name even for queues that don't register
+	 * a gendisk, so it lazily registers the debugfs directory.  But that
+	 * can get us into a situation where a SCSI device is found, with no
+	 * driver for it (yet).  Then blktrace is used on the device, creating
+	 * the debugfs directory, and only after that a drivers is loaded. In
+	 * that case we might already have a debugfs directory registered here.
+	 * Even worse we could be racing with blktrace to register it.
+	 */
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	mutex_lock(&q->blk_trace_mutex);
+	if (!q->debugfs_dir) {
+		q->debugfs_dir =
+			debugfs_create_dir(kobject_name(q->kobj.parent),
+				blk_debugfs_root);
+	}
+	mutex_unlock(&q->blk_trace_mutex);
+#else
+	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
+					    blk_debugfs_root);
+#endif
+
 	if (queue_is_mq(q)) {
 		__blk_mq_register_dev(dev, q);
 		blk_mq_debugfs_register(q);

index 5db4ec1e85f7..f11f79295419 100644
@@ -14,9 +14,7 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
-#ifdef CONFIG_DEBUG_FS
 extern struct dentry *blk_debugfs_root;
-#endif
 
 struct blk_flush_queue {
 	unsigned int		flush_pending_idx:1;

index 297004fd2264..95f9019aac83 100644
@@ -10,6 +10,7 @@
 #include <linux/vmalloc.h>
 #include <linux/blktrace_api.h>
 #include <linux/raid/detect.h>
+#include <linux/debugfs.h>
 #include "check.h"
 
 static int (*check_part[])(struct parsed_partitions *) = {

@@ -322,6 +323,7 @@ void delete_partition(struct gendisk *disk, struct hd_struct *part)
 	get_device(disk_to_dev(part_to_disk(part)));
 	rcu_assign_pointer(ptbl->part[part->partno], NULL);
 	kobject_put(part->holder_dir);
+	debugfs_remove_recursive(part->debugfs_dir);
 	device_del(part_to_dev(part));
 
 	/*

@@ -443,6 +445,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!p->holder_dir)
 		goto out_del;
 
+	p->debugfs_dir = debugfs_create_dir(dev_name(pdev), blk_debugfs_root);
 	dev_set_uevent_suppress(pdev, 0);
 	if (flags & ADDPART_FLAG_WHOLEDISK) {
 		err = device_create_file(pdev, &dev_attr_whole_disk);

index 20e378b428b8..737467c29a31 100644
@@ -574,8 +574,8 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
 
-#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
+#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
 #endif

index 3b6ff5902edc..eb6db276e293 100644
@@ -22,7 +22,6 @@ struct blk_trace {
 	u64 end_lba;
 	u32 pid;
 	u32 dev;
-	struct dentry *dir;
 	struct dentry *dropped_file;
 	struct dentry *msg_file;
 	struct list_head running_list;

index a9384449465a..7ff4c4c06140 100644
@@ -89,6 +89,7 @@ struct hd_struct {
 	int make_it_fail;
 #endif
 	struct rcu_work rcu_work;
+	struct dentry *debugfs_dir;
 };
 
 /**

74 lines not on this page · raw message

index 86c107de2836..f46bdc7f6509 100644
@@ -920,6 +920,9 @@ static void blk_release_queue(struct kobject *kobj)
 	blk_trace_shutdown(q);
 
 	debugfs_remove_recursive(q->debugfs_dir);
+#if defined(CONFIG_CHR_DEV_SG) || defined(CONFIG_CHR_DEV_SG_MODULE)
+	debugfs_remove_recursive(q->sg_debugfs_dir);
+#endif
 	if (queue_is_mq(q))
 		blk_mq_debugfs_unregister(q);
 

@@ -939,6 +942,21 @@ struct kobj_type blk_queue_ktype = {
 	.release	= blk_release_queue,
 };
 
+#if defined(CONFIG_CHR_DEV_SG) || defined(CONFIG_CHR_DEV_SG_MODULE)
+/**
+ * blk_sg_debugfs_init - initialize debugs for scsi-generic
+ * @q: the associated queue
+ * @name: name of the scsi-generic device
+ *
+ * To be used by scsi-generic for allowing it to use blktrace.
+ */
+void blk_sg_debugfs_init(struct request_queue *q, const char *name)
+{
+	q->sg_debugfs_dir = debugfs_create_dir(name, blk_debugfs_root);
+}
+EXPORT_SYMBOL_GPL(blk_sg_debugfs_init);
+#endif
+
 /**
  * blk_register_queue - register a block layer queue with sysfs
  * @disk: Disk of which the request queue should be registered with sysfs.

index 20472aaaf630..c87fe1923f3d 100644
@@ -1519,6 +1519,7 @@ static int
 sg_add_device(struct device *cl_dev, struct class_interface *cl_intf)
 {
 	struct scsi_device *scsidp = to_scsi_device(cl_dev->parent);
+	struct request_queue *q = scsidp->request_queue;
 	struct gendisk *disk;
 	Sg_device *sdp = NULL;
 	struct cdev * cdev = NULL;

@@ -1573,6 +1574,7 @@ sg_add_device(struct device *cl_dev, struct class_interface *cl_intf)
 	} else
 		pr_warn("%s: sg_sys Invalid\n", __func__);
 
+	blk_sg_debugfs_init(q, disk->disk_name);
 	sdev_printk(KERN_NOTICE, scsidp, "Attached scsi generic sg%d "
 		    "type %d\n", sdp->index, scsidp->type);
 

index 5877b03b8117..be5a40d59f60 100644
@@ -575,6 +575,9 @@ struct request_queue {
 	struct bio_set		bio_split;
 
 	struct dentry		*debugfs_dir;
+#if defined(CONFIG_CHR_DEV_SG) || defined(CONFIG_CHR_DEV_SG_MODULE)
+	struct dentry		*sg_debugfs_dir;
+#endif
 #ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;

@@ -858,6 +861,14 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
+#if defined(CONFIG_CHR_DEV_SG) || defined(CONFIG_CHR_DEV_SG_MODULE)
+extern void blk_sg_debugfs_init(struct request_queue *q, const char *name);
+#else
+static inline void blk_sg_debugfs_init(struct request_queue *q,
+				       const char *name)
+{
+}
+#endif
 extern blk_qc_t generic_make_request(struct bio *bio);
 extern blk_qc_t direct_make_request(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);

index a55cbfd060f5..5b0310f38e11 100644
@@ -511,6 +511,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 */
 	if (bdev && bdev != bdev->bd_contains) {
 		dir = bdev->bd_part->debugfs_dir;
+	} else if (q->sg_debugfs_dir &&
+		   strlen(buts->name) == strlen(q->sg_debugfs_dir->d_name.name)
+		   && strcmp(buts->name, q->sg_debugfs_dir->d_name.name) == 0) {
+		/* scsi-generic requires use of its own directory */
+		dir = q->sg_debugfs_dir;
 	} else {
 		/*
 		 * For queues that do not have a gendisk attached to them, that

index 6c10a1427de2..ac6650828d49 100644
@@ -3,6 +3,9 @@
  * Copyright (C) 2006 Jens Axboe <[email protected]>
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>

@@ -493,6 +496,16 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 */
 	strreplace(buts->name, '/', '_');
 
+	/*
+	 * bdev can be NULL, as with scsi-generic, this is a helpful as
+	 * we can be.
+	 */
+	if (q->blk_trace) {
+		pr_warn("Concurrent blktraces are not allowed on %s\n",
+			buts->name);
+		return -EBUSY;
+	}
+
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
 		return -ENOMEM;

index 14372df0f354..54fbcbd930de 100644
@@ -2333,6 +2333,8 @@ static void __exit loop_exit(void)
 
 	range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
 
+	mutex_lock(&loop_ctl_mutex);
+
 	idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
 	idr_destroy(&loop_index_idr);
 

@@ -2340,6 +2342,8 @@ static void __exit loop_exit(void)
 	unregister_blkdev(LOOP_MAJOR, "loop");
 
 	misc_deregister(&loop_misc);
+
+	mutex_unlock(&loop_ctl_mutex);
 }
 
 module_init(loop_init);