Blob Blame History Raw
From 1d49eb91e86e8c1c1614c72e3e958b6b7e2472a9 Mon Sep 17 00:00:00 2001
From: Ioanna Alifieraki <ioanna-maria.alifieraki@canonical.com>
Date: Mon, 15 Nov 2021 15:16:45 +0200
Subject: [PATCH] ipmi: Move remove_work to dedicated workqueue
Git-commit: 1d49eb91e86e8c1c1614c72e3e958b6b7e2472a9
References: git-fixes
Patch-mainline: v5.16-rc4

Currently when removing an ipmi_user the removal is deferred as a work on
the system's workqueue. Although this guarantees the free operation will
occur in non atomic context, it can race with the ipmi_msghandler module
removal (see [1]) . In case a remove_user work is scheduled for removal
and shortly after ipmi_msghandler module is removed we can end up in a
situation where the module is removed fist and when the work is executed
the system crashes with :
BUG: unable to handle page fault for address: ffffffffc05c3450
PF: supervisor instruction fetch in kernel mode
PF: error_code(0x0010) - not-present page
because the pages of the module are gone. In cleanup_ipmi() there is no
easy way to detect if there are any pending works to flush them before
removing the module. This patch creates a separate workqueue and schedules
the remove_work works on it. When removing the module the workqueue is
drained when destroyed to avoid the race.

[1] https://bugs.launchpad.net/bugs/1950666

Cc: stable@vger.kernel.org # 5.1
Fixes: 3b9a907223d7 (ipmi: fix sleep-in-atomic in free_user at cleanup SRCU user->release_barrier)
Signed-off-by: Ioanna Alifieraki <ioanna-maria.alifieraki@canonical.com>
Message-Id: <20211115131645.25116-1-ioanna-maria.alifieraki@canonical.com>
Signed-off-by: Corey Minyard <cminyard@mvista.com>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
---
 drivers/char/ipmi/ipmi_msghandler.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -221,6 +221,8 @@ struct ipmi_user {
 	struct work_struct remove_work;
 };
 
+struct workqueue_struct *remove_work_wq;
+
 static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
 	__acquires(user->release_barrier)
 {
@@ -1226,7 +1228,7 @@ static void free_user(struct kref *ref)
 	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
 
 	/* SRCU cleanup must happen in task context. */
-	schedule_work(&user->remove_work);
+	queue_work(remove_work_wq, &user->remove_work);
 }
 
 static void _ipmi_destroy_user(struct ipmi_user *user)
@@ -5330,10 +5332,17 @@ static int ipmi_init_msghandler(void)
 	mod_timer(&ipmi_timer, jiffies + IPMI_TIMEOUT_JIFFIES);
 
 	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+	remove_work_wq = create_singlethread_workqueue("ipmi-msghandler-remove-wq");
+	if (!remove_work_wq) {
+		pr_err("unable to create ipmi-msghandler-remove-wq workqueue");
+		rv = -ENOMEM;
+		goto out;
+	}
 
 	initialized = 1;
 
-	return 0;
+out:
+	return rv;
 }
 
 static int __init ipmi_init_msghandler_mod(void)
@@ -5349,6 +5358,7 @@ static void __exit cleanup_ipmi(void)
 	if (!initialized)
 		return;
 
+	destroy_workqueue(remove_work_wq);
 	atomic_notifier_chain_unregister(&panic_notifier_list, &panic_block);
 
 	/*