[kernel/f17] Fix oops on aoe module removal (rhbz 853064)

Fri Jan 4 13:13:27 UTC 2013

commit bf1ab342543ff1d2d12e12fdf227fa18ccf44326
Author: Josh Boyer <jwboyer at redhat.com>
Date:   Fri Jan 4 08:08:18 2013 -0500

    Fix oops on aoe module removal (rhbz 853064)

 aoe-remove-extra-bdi_init.patch |   78 +++++++++++++++++++++++++++++++++++++++
 kernel.spec                     |   11 +++++-
 2 files changed, 88 insertions(+), 1 deletions(-)
---

diff --git a/aoe-remove-extra-bdi_init.patch b/aoe-remove-extra-bdi_init.patch
new file mode 100644
index 0000000..7275d53
--- /dev/null
+++ b/aoe-remove-extra-bdi_init.patch
@@ -0,0 +1,78 @@
+Lines: 75
+
+On Thu, Jan 03, 2013 at 12:15:35PM -0600, Ed Cashin wrote:
+...
+> >>>>> On Jan 3, 2013, at 8:25 AM, Josh Boyer wrote:
+...
+> >>>>>> [699170.611997] aoe: AoE v47 initialised.
+...
+> >>>>>> [699231.308319] WARNING: at lib/list_debug.c:62 __list_del_entry+0x82/0xd0()
+> >>>>>> [699231.312031] Hardware name: S5000VSA
+> >>>>>> [699231.315658] list_del corruption. next->prev should be ffff880009fa37e8, but was ffffffff81c79c00
+> >>>>>> [699231.319352] Modules linked in: aoe(-) ip6table_filter ip6_tables ebtable_nat ebtables lockd sunrpc bridge 8021q garp stp llc vfat fat binfmt_misc iTCO_wdt iTCO_vendor_support vhost_net lpc_ich radeon tun macvtap mfd_core serio_raw coretemp i2c_algo_bit ttm i5000_edac macvlan drm_kms_helper e1000e edac_core microcode i5k_amb shpchp i2c_i801 drm kvm_intel i2c_core kvm ioatdma dca raid1
+> >>>>>> [699231.336259] Pid: 8584, comm: modprobe Not tainted 3.6.11-1.fc17.x86_64 #1
+> >>>>>> [699231.340561] Call Trace:
+> >>>>>> [699231.344865]  [<ffffffff8105c8ef>] warn_slowpath_common+0x7f/0xc0
+> >>>>>> [699231.349212]  [<ffffffff8105c9e6>] warn_slowpath_fmt+0x46/0x50
+> >>>>>> [699231.353595]  [<ffffffff812eee52>] __list_del_entry+0x82/0xd0
+> >>>>>> [699231.357954]  [<ffffffff812eeeb1>] list_del+0x11/0x40
+> >>>>>> [699231.362319]  [<ffffffff812f6458>] percpu_counter_destroy+0x28/0x50
+> >>>>>> [699231.366712]  [<ffffffff8114c513>] bdi_destroy+0x43/0x140
+> >>>>>> [699231.371127]  [<ffffffff812be20c>] blk_release_queue+0x8c/0xc0
+> >>>>>> [699231.375454]  [<ffffffff812dc322>] kobject_cleanup+0x82/0x1b0
+> >>>>>> [699231.379675]  [<ffffffff812dc1ab>] kobject_put+0x2b/0x60
+> >>>>>> [699231.383851]  [<ffffffff812b80a5>] blk_put_queue+0x15/0x20
+> >>>>>> [699231.387899]  [<ffffffff812bc659>] blk_cleanup_queue+0xc9/0xe0
+> >>>>>> [699231.391794]  [<ffffffffa01f53f5>] aoedev_freedev+0x135/0x150 [aoe]
+> >>>>>> [699231.395668]  [<ffffffffa01f59a5>] aoedev_exit+0x65/0x80 [aoe]
+> >>>>>> [699231.399493]  [<ffffffffa01f5afe>] aoe_exit+0x2e/0x40 [aoe]
+> >>>>>> [699231.403273]  [<ffffffff810bdefe>] sys_delete_module+0x16e/0x2d0
+> >>>>>> [699231.407119]  [<ffffffff8161db56>] ? __schedule+0x3c6/0x7a0
+> >>>>>> [699231.411050]  [<ffffffff8119054a>] ? sys_write+0x4a/0x90
+> >>>>>> [699231.415033]  [<ffffffff81627329>] system_call_fastpath+0x16/0x1b
+> >>>>>> [699231.419117] ---[ end trace 9e1558af1964b569 ]---
+> >>>>>> [699231.423248] ------------[ cut here ]------------
+
+The blk_alloc_queue has already done a bdi_init, so do not bdi_init again in
+aoeblk_gdalloc.
+
+The patch below applies to v3.5.6, with its v47 aoe driver.  On my system it
+eliminates the list_del corruption messages.
+
+It updates VERSION for convenience during testing.
+
+diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
+index db195ab..2ccb9e2 100644
+--- a/drivers/block/aoe/aoe.h
++++ b/drivers/block/aoe/aoe.h
+@@ -1,5 +1,5 @@
+ /* Copyright (c) 2007 Coraid, Inc.  See COPYING for GPL terms. */
+-#define VERSION "47"
++#define VERSION "47nobdi1"
+ #define AOE_MAJOR 152
+ #define DEVICE_NAME "aoe"
+ 
+diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
+index 321de7b..7eca463 100644
+--- a/drivers/block/aoe/aoeblk.c
++++ b/drivers/block/aoe/aoeblk.c
+@@ -276,8 +276,6 @@ aoeblk_gdalloc(void *vp)
+ 		goto err_mempool;
+ 	blk_queue_make_request(d->blkq, aoeblk_make_request);
+ 	d->blkq->backing_dev_info.name = "aoe";
+-	if (bdi_init(&d->blkq->backing_dev_info))
+-		goto err_blkq;
+ 	spin_lock_irqsave(&d->lock, flags);
+ 	gd->major = AOE_MAJOR;
+ 	gd->first_minor = d->sysminor * AOE_PARTITIONS;
+@@ -298,9 +296,6 @@ aoeblk_gdalloc(void *vp)
+ 	aoedisk_add_sysfs(d);
+ 	return;
+ 
+-err_blkq:
+-	blk_cleanup_queue(d->blkq);
+-	d->blkq = NULL;
+ err_mempool:
+ 	mempool_destroy(d->bufpool);
+ err_disk:
+
diff --git a/kernel.spec b/kernel.spec
index 01eb6ef..a1e8d14 100644
--- a/kernel.spec
+++ b/kernel.spec
@@ -54,7 +54,7 @@ Summary: The Linux kernel
 # For non-released -rc kernels, this will be appended after the rcX and
 # gitX tags, so a 3 here would become part of release "0.rcX.gitX.3"
 #
-%global baserelease 3
+%global baserelease 4
 %global fedora_build %{baserelease}
 
 # base_sublevel is the kernel version we're starting with and patching
@@ -790,6 +790,9 @@ Patch21237: 0001-ACPI-sony-laptop-do-proper-memcpy-for-ACPI_TYPE_INTE.patch
 #rhbz 874372
 Patch21238: don-t-do-blind-d_drop-in-nfs_prime_dcache.patch
 
+#rhbz 853064
+Patch21239: aoe-remove-extra-bdi_init.patch
+
 # END OF PATCH DEFINITIONS
 
 %endif
@@ -1534,6 +1537,9 @@ ApplyPatch 0001-ACPI-sony-laptop-do-proper-memcpy-for-ACPI_TYPE_INTE.patch
 #rhbz 874372
 ApplyPatch don-t-do-blind-d_drop-in-nfs_prime_dcache.patch
 
+#rhbz 853064
+ApplyPatch aoe-remove-extra-bdi_init.patch
+
 
 # END OF PATCH APPLICATIONS
 
@@ -2398,6 +2404,9 @@ fi
 #    '-'      |  |
 #              '-'
 %changelog
+* Fri Jan 04 2013 Josh Boyer <jwboyer at redhat.com>
+- Fix oops on aoe module removal (rhbz 853064)
+
 * Wed Jan 02 2013 Josh Boyer <jwboyer at redhat.com>
 - Fix autofs issue in 3.6 (rhbz 874372)
 - BR the hostname package (rhbz 886113)
