Merge tag 'driver-core-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core updates from Greg KH:
 "Here is the set of driver core changes for 5.19-rc1.

  Lots of tiny driver core changes and cleanups happened this cycle, but
  the two major things are:

   - firmware_loader reorganization and additions including the ability
     to have XZ compressed firmware images and the ability for userspace
     to initiate the firmware load when it needs to, instead of being
     always initiated by the kernel. FPGA devices specifically want this
     ability to have their firmware changed over the lifetime of the
     system boot, and this allows them to work without having to come up
     with yet-another-custom-uapi interface for loading firmware for
     them.

   - physical location support added to sysfs so that devices that know
     this information, can tell userspace where they are located in a
     common way. Some ACPI devices already support this today, and more
     bus types should support this in the future.

  Smaller changes include:

   - driver_override api cleanups and fixes

   - error path cleanups and fixes

   - get_abi script fixes

   - deferred probe timeout changes.

  It's that last change that I'm the most worried about. It has been
  reported to cause boot problems for a number of systems, and I have a
  tested patch series that resolves this issue. But I didn't get it
  merged into my tree before 5.18-final came out, so it has not gotten
  any linux-next testing.

  I'll send the fixup patches (there are 2) as a follow-on series to this
  pull request.

  All have been tested in linux-next for weeks, with no reported issues
  other than the above-mentioned boot time-outs"

* tag 'driver-core-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (55 commits)
  driver core: fix deadlock in __device_attach
  kernfs: Separate kernfs_pr_cont_buf and rename_lock.
  topology: Remove unused cpu_cluster_mask()
  driver core: Extend deferred probe timeout on driver registration
  MAINTAINERS: add Russ Weight as a firmware loader maintainer
  driver: base: fix UAF when driver_attach failed
  test_firmware: fix end of loop test in upload_read_show()
  driver core: location: Add "back" as a possible output for panel
  driver core: location: Free struct acpi_pld_info *pld
  driver core: Add "*" wildcard support to driver_async_probe cmdline param
  driver core: location: Check for allocations failure
  arch_topology: Trace the update thermal pressure
  kernfs: Rename kernfs_put_open_node to kernfs_unlink_open_file.
  export: fix string handling of namespace in EXPORT_SYMBOL_NS
  rpmsg: use local 'dev' variable
  rpmsg: Fix calling device_lock() on non-initialized device
  firmware_loader: describe 'module' parameter of firmware_upload_register()
  firmware_loader: Move definitions from sysfs_upload.h to sysfs.h
  firmware_loader: Fix configs for sysfs split
  selftests: firmware: Add firmware upload selftests
  ...

2 files changed, 45 insertions, 33 deletions

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index e205fde7163a..6eca72cfa1f2 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -18,7 +18,15 @@
 #include "kernfs-internal.h"
 
 static DEFINE_SPINLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
-static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by rename_lock */
+/*
+ * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to
+ * call pr_cont() while holding rename_lock. Because sometimes pr_cont()
+ * will perform wakeups when releasing console_sem. Holding rename_lock
+ * will introduce deadlock if the scheduler reads the kernfs_name in the
+ * wakeup path.
+ */
+static DEFINE_SPINLOCK(kernfs_pr_cont_lock);
+static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by pr_cont_lock */
 static DEFINE_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
@@ -229,12 +237,12 @@ void pr_cont_kernfs_name(struct kernfs_node *kn)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+	kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
 	pr_cont("%s", kernfs_pr_cont_buf);
 
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -248,10 +256,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	unsigned long flags;
 	int sz;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf,
-					  sizeof(kernfs_pr_cont_buf));
+	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
+				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
 		pr_cont("(error)");
 		goto out;
@@ -265,7 +273,7 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	pr_cont("%s", kernfs_pr_cont_buf);
 
 out:
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -823,13 +831,12 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 
 	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
-	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
-	spin_lock_irq(&kernfs_rename_lock);
+	spin_lock_irq(&kernfs_pr_cont_lock);
 
 	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
 	if (len >= sizeof(kernfs_pr_cont_buf)) {
-		spin_unlock_irq(&kernfs_rename_lock);
+		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
 
@@ -841,7 +848,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 		parent = kernfs_find_ns(parent, name, ns);
 	}
 
-	spin_unlock_irq(&kernfs_rename_lock);
+	spin_unlock_irq(&kernfs_pr_cont_lock);
 
 	return parent;
 }
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 88423069407c..e3abfa843879 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -33,7 +33,6 @@ static DEFINE_SPINLOCK(kernfs_open_node_lock);
 static DEFINE_MUTEX(kernfs_open_file_mutex);
 
 struct kernfs_open_node {
-	atomic_t		refcnt;
 	atomic_t		event;
 	wait_queue_head_t	poll;
 	struct list_head	files; /* goes through kernfs_open_file.list */
@@ -530,10 +529,8 @@ static int kernfs_get_open_node(struct kernfs_node *kn,
 	}
 
 	on = kn->attr.open;
-	if (on) {
-		atomic_inc(&on->refcnt);
+	if (on)
 		list_add_tail(&of->list, &on->files);
-	}
 
 	spin_unlock_irq(&kernfs_open_node_lock);
 	mutex_unlock(&kernfs_open_file_mutex);
@@ -548,7 +545,6 @@ static int kernfs_get_open_node(struct kernfs_node *kn,
 	if (!new_on)
 		return -ENOMEM;
 
-	atomic_set(&new_on->refcnt, 0);
 	atomic_set(&new_on->event, 1);
 	init_waitqueue_head(&new_on->poll);
 	INIT_LIST_HEAD(&new_on->files);
@@ -556,17 +552,19 @@ static int kernfs_get_open_node(struct kernfs_node *kn,
 }
 
 /**
- *	kernfs_put_open_node - put kernfs_open_node
- *	@kn: target kernfs_nodet
+ *	kernfs_unlink_open_file - Unlink @of from @kn.
+ *
+ *	@kn: target kernfs_node
  *	@of: associated kernfs_open_file
  *
- *	Put @kn->attr.open and unlink @of from the files list.  If
- *	reference count reaches zero, disassociate and free it.
+ *	Unlink @of from list of @kn's associated open files. If list of
+ *	associated open files becomes empty, disassociate and free
+ *	kernfs_open_node.
  *
  *	LOCKING:
  *	None.
  */
-static void kernfs_put_open_node(struct kernfs_node *kn,
+static void kernfs_unlink_open_file(struct kernfs_node *kn,
 				 struct kernfs_open_file *of)
 {
 	struct kernfs_open_node *on = kn->attr.open;
@@ -578,7 +576,7 @@ static void kernfs_put_open_node(struct kernfs_node *kn,
 	if (of)
 		list_del(&of->list);
 
-	if (atomic_dec_and_test(&on->refcnt))
+	if (list_empty(&on->files))
 		kn->attr.open = NULL;
 	else
 		on = NULL;
@@ -706,7 +704,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	return 0;
 
 err_put_node:
-	kernfs_put_open_node(kn, of);
+	kernfs_unlink_open_file(kn, of);
 err_seq_release:
 	seq_release(inode, file);
 err_free:
@@ -752,7 +750,7 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp)
 		mutex_unlock(&kernfs_open_file_mutex);
 	}
 
-	kernfs_put_open_node(kn, of);
+	kernfs_unlink_open_file(kn, of);
 	seq_release(inode, filp);
 	kfree(of->prealloc_buf);
 	kfree(of);
@@ -768,15 +766,24 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
 	if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE)))
 		return;
 
-	spin_lock_irq(&kernfs_open_node_lock);
-	on = kn->attr.open;
-	if (on)
-		atomic_inc(&on->refcnt);
-	spin_unlock_irq(&kernfs_open_node_lock);
-	if (!on)
+	/*
+	 * lockless opportunistic check is safe below because no one is adding to
+	 * ->attr.open at this point of time. This check allows early bail out
+	 * if ->attr.open is already NULL. kernfs_unlink_open_file makes
+	 * ->attr.open NULL only while holding kernfs_open_file_mutex so below
+	 * check under kernfs_open_file_mutex will ensure bailing out if
+	 * ->attr.open became NULL while waiting for the mutex.
+	 */
+	if (!kn->attr.open)
 		return;
 
 	mutex_lock(&kernfs_open_file_mutex);
+	if (!kn->attr.open) {
+		mutex_unlock(&kernfs_open_file_mutex);
+		return;
+	}
+
+	on = kn->attr.open;
 
 	list_for_each_entry(of, &on->files, list) {
 		struct inode *inode = file_inode(of->file);
@@ -789,8 +796,6 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
 	}
 
 	mutex_unlock(&kernfs_open_file_mutex);
-
-	kernfs_put_open_node(kn, NULL);
 }
 
 /*