Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759492AbcCVLVo (ORCPT ); Tue, 22 Mar 2016 07:21:44 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:56374 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758652AbcCVKlk (ORCPT ); Tue, 22 Mar 2016 06:41:40 -0400 From: Luis Henriques To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: James Bottomley , Luis Henriques Subject: [PATCH 3.16.y-ckt 010/142] scsi: fix soft lockup in scsi_remove_target() on module removal Date: Tue, 22 Mar 2016 10:38:59 +0000 Message-Id: <1458643271-4227-11-git-send-email-luis.henriques@canonical.com> In-Reply-To: <1458643271-4227-1-git-send-email-luis.henriques@canonical.com> References: <1458643271-4227-1-git-send-email-luis.henriques@canonical.com> X-Extended-Stable: 3.16 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4315 Lines: 81 3.16.7-ckt26 -stable review patch. If anyone has any objections, please let me know. ---8<------------------------------------------------------------ From: James Bottomley commit 90a88d6ef88edcfc4f644dddc7eef4ea41bccf8b upstream. This softlockup is currently happening: [ 444.088002] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/1:1:29] [ 444.088002] Modules linked in: lpfc(-) qla2x00tgt(O) qla2xxx_scst(O) scst_vdisk(O) scsi_transport_fc libcrc32c scst(O) dlm configfs nfsd lockd grace nfs_acl auth_rpcgss sunrpc ed d snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device dm_mod iTCO_wdt snd_hda_codec_realtek snd_hda_codec_generic gpio_ich iTCO_vendor_support ppdev snd_hda_intel snd_hda_codec snd_hda _core snd_hwdep tg3 snd_pcm snd_timer libphy lpc_ich parport_pc ptp acpi_cpufreq snd pps_core fjes parport i2c_i801 ehci_pci tpm_tis tpm sr_mod cdrom soundcore floppy hwmon sg 8250_ fintek pcspkr i915 drm_kms_helper uhci_hcd ehci_hcd drm fb_sys_fops sysimgblt sysfillrect syscopyarea i2c_algo_bit usbcore button video usb_common fan ata_generic ata_piix libata th ermal [ 444.088002] CPU: 1 PID: 29 Comm: kworker/1:1 Tainted: G O 4.4.0-rc5-2.g1e923a3-default #1 [ 444.088002] Hardware name: FUJITSU SIEMENS ESPRIMO E /D2164-A1, BIOS 5.00 R1.10.2164.A1 05/08/2006 [ 444.088002] Workqueue: fc_wq_4 fc_rport_final_delete [scsi_transport_fc] [ 444.088002] task: f6266ec0 ti: f6268000 task.ti: f6268000 [ 444.088002] EIP: 0060:[] EFLAGS: 00000286 CPU: 1 [ 444.088002] EIP is at _raw_spin_unlock_irqrestore+0x14/0x20 [ 444.088002] EAX: 00000286 EBX: f20d3800 ECX: 00000002 EDX: 00000286 [ 444.088002] ESI: f50ba800 EDI: f2146848 EBP: f6269ec8 ESP: f6269ec8 [ 444.088002] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 [ 444.088002] CR0: 8005003b CR2: 08f96600 CR3: 363ae000 CR4: 000006d0 [ 444.088002] Stack: [ 444.088002] f6269eec c066b0f7 00000286 f2146848 f50ba808 f50ba800 f50ba800 f2146a90 [ 444.088002] f2146848 f6269f08 f8f0a4ed f3141000 f2146800 f2146a90 f619fa00 00000040 [ 444.088002] f6269f40 c026cb25 00000001 166c6392 00000061 f6757140 f6136340 00000004 [ 444.088002] Call Trace: [ 444.088002] [] scsi_remove_target+0x167/0x1c0 [ 444.088002] [] fc_rport_final_delete+0x9d/0x1e0 [scsi_transport_fc] [ 444.088002] [] process_one_work+0x155/0x3e0 [ 444.088002] [] worker_thread+0x37/0x490 [ 444.088002] [] kthread+0x9b/0xb0 [ 444.088002] [] ret_from_kernel_thread+0x21/0x40 What appears to be happening is that something has pinned the target so it can't go into STARGET_DEL via final release and the loop in scsi_remove_target spins endlessly until that happens. The fix for this soft lockup is to not keep looping over a device that we've called remove on but which hasn't gone into DEL state. This patch will retain a simplistic memory of the last target and not keep looping over it. Reported-by: Sebastian Herbszt Tested-by: Sebastian Herbszt Fixes: 40998193560dab6c3ce8d25f4fa58a23e252ef38 Signed-off-by: James Bottomley Signed-off-by: Luis Henriques --- drivers/scsi/scsi_sysfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 7e78015d6ab7..6c26b9743c52 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1148,16 +1148,18 @@ static void __scsi_remove_target(struct scsi_target *starget) void scsi_remove_target(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev->parent); - struct scsi_target *starget; + struct scsi_target *starget, *last_target = NULL; unsigned long flags; restart: spin_lock_irqsave(shost->host_lock, flags); list_for_each_entry(starget, &shost->__targets, siblings) { - if (starget->state == STARGET_DEL) + if (starget->state == STARGET_DEL || + starget == last_target) continue; if (starget->dev.parent == dev || &starget->dev == dev) { kref_get(&starget->reap_ref); + last_target = starget; spin_unlock_irqrestore(shost->host_lock, flags); __scsi_remove_target(starget); scsi_target_reap(starget);