elevator: fix oops on early call to elevator_change()

2.6.36 introduces an API for drivers to switch the IO scheduler
instead of manually calling the elevator exit and init functions.
This API was added since q->elevator must be cleared in between
those two calls. And since we already have this functionality
directly from use by the sysfs interface to switch schedulers
online, it was prudent to reuse it internally too.

But this API needs the queue to be in a fully initialized state
before it is called, or it will attempt to unregister elevator
kobjects before they have been added. This results in an oops
like this:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000051
IP: [<ffffffff8116f15e>] sysfs_create_dir+0x2e/0xc0
PGD 47ddfc067 PUD 47c6a1067 PMD 0
Oops: 0000 [#1] PREEMPT SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:04:00.1/irq
CPU 2
Modules linked in: t(+) loop hid_apple usbhid ahci ehci_hcd uhci_hcd libahci usbcore nls_base igb

Pid: 7319, comm: modprobe Not tainted 2.6.36-rc6+ #132 QSSC-S4R/QSSC-S4R
RIP: 0010:[<ffffffff8116f15e>]  [<ffffffff8116f15e>] sysfs_create_dir+0x2e/0xc0
RSP: 0018:ffff88027da25d08  EFLAGS: 00010246
RAX: ffff88047c68c528 RBX: 00000000fffffffe RCX: 0000000000000000
RDX: 000000000000002f RSI: 000000000000002f RDI: ffff88047e196c88
RBP: ffff88027da25d38 R08: 0000000000000000 R09: d84156c5635688c0
R10: d84156c5635688c0 R11: 0000000000000000 R12: ffff88047e196c88
R13: 0000000000000000 R14: 0000000000000000 R15: ffff88047c68c528
FS:  00007fcb0b26f6e0(0000) GS:ffff880287400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000051 CR3: 000000047e76e000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process modprobe (pid: 7319, threadinfo ffff88027da24000, task ffff88027d377090)
Stack:
 ffff88027da25d58 ffff88047c68c528 00000000fffffffe ffff88047e196c88
<0> ffff88047c68c528 ffff88047e05bd90 ffff88027da25d78 ffffffff8123fb77
<0> ffff88047e05bd90 0000000000000000 ffff88047e196c88 ffff88047c68c528
Call Trace:
 [<ffffffff8123fb77>] kobject_add_internal+0xe7/0x1f0
 [<ffffffff8123fd98>] kobject_add_varg+0x38/0x60
 [<ffffffff8123feb9>] kobject_add+0x69/0x90
 [<ffffffff8116efe0>] ? sysfs_remove_dir+0x20/0xa0
 [<ffffffff8103d48d>] ? sub_preempt_count+0x9d/0xe0
 [<ffffffff8143de20>] ? _raw_spin_unlock+0x30/0x50
 [<ffffffff8116efe0>] ? sysfs_remove_dir+0x20/0xa0
 [<ffffffff8116eff4>] ? sysfs_remove_dir+0x34/0xa0
 [<ffffffff81224204>] elv_register_queue+0x34/0xa0
 [<ffffffff81224aad>] elevator_change+0xfd/0x250
 [<ffffffffa007e000>] ? t_init+0x0/0x361 [t]
 [<ffffffffa007e000>] ? t_init+0x0/0x361 [t]
 [<ffffffffa007e0a8>] t_init+0xa8/0x361 [t]
 [<ffffffff810001de>] do_one_initcall+0x3e/0x170
 [<ffffffff8108c3fd>] sys_init_module+0xbd/0x220
 [<ffffffff81002f2b>] system_call_fastpath+0x16/0x1b
Code: e5 41 56 41 55 41 54 49 89 fc 53 48 83 ec 10 48 85 ff 74 52 48 8b 47 18 49 c7 c5 00 46 61 81 48 85 c0 74 04 4c 8b 68 30 45 31 f6 <41> 80 7d 51 00 74 0e 49 8b 44 24 28 4c 89 e7 ff 50 20 49 89 c6
RIP  [<ffffffff8116f15e>] sysfs_create_dir+0x2e/0xc0
 RSP <ffff88027da25d08>
CR2: 0000000000000051
---[ end trace a6541d3bf07945df ]---

Fix this by adding a registered bit to the elevator queue, which is
set when the sysfs kobjects have been registered.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

diff --git a/block/elevator.c b/block/elevator.c
index 205b09a5bd9ead9e64d7bcfb60cec924f1a22cbd..4e11559aa2b02d78c4d90c104e81e7a2e84aa05d 100644 (file)
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -938,6 +938,7 @@ int elv_register_queue(struct request_queue *q)
                        }
                }
                kobject_uevent(&e->kobj, KOBJ_ADD);
+               e->registered = 1;
        }
        return error;
 }
@@ -947,6 +948,7 @@ static void __elv_unregister_queue(struct elevator_queue *e)
 {
        kobject_uevent(&e->kobj, KOBJ_REMOVE);
        kobject_del(&e->kobj);
+       e->registered = 0;
 }
 
 void elv_unregister_queue(struct request_queue *q)
@@ -1042,11 +1044,13 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
        spin_unlock_irq(q->queue_lock);
 
-       __elv_unregister_queue(old_elevator);
+       if (old_elevator->registered) {
+               __elv_unregister_queue(old_elevator);
 
-       err = elv_register_queue(q);
-       if (err)
-               goto fail_register;
+               err = elv_register_queue(q);
+               if (err)
+                       goto fail_register;
+       }
 
        /*
         * finally exit old elevator and turn off BYPASS.

diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 926b50322a469c9d16c48ed35e10c4c12bd695f3..4fd978e7eb83ef8d689d0d313b5441b0631ea275 100644 (file)
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -93,6 +93,7 @@ struct elevator_queue
        struct elevator_type *elevator_type;
        struct mutex sysfs_lock;
        struct hlist_head *hash;
+       unsigned int registered:1;
 };
 
 /*