On 10/29/18 8:50 AM, Jens Axboe wrote:
> On 10/29/18 6:00 AM, Ming Lei wrote:
>> On Thu, Oct 25, 2018 at 03:10:11PM -0600, Jens Axboe wrote:
>>> The first round of this went into 4.20-rc, but we've still some of
>>> them pending. This patch series converts the remaining drivers to
>>> blk-mq. The ones that support dual paths (like SCSI and DM) have
>>> the non-mq path removed. At the end, legacy IO code and schedulers
>>> are killed off.
>>>
>>> This patch series is on top of my for-linus branch. It can also
>>> be bound in my mq-conversions branch.
>>>
>>> Documentation/block/biodoc.txt | 88 -
>>> Documentation/block/cfq-iosched.txt | 291 --
>>> Documentation/scsi/scsi-parameters.txt | 5 -
>>> block/Kconfig | 6 -
>>> block/Kconfig.iosched | 61 -
>>> block/Makefile | 5 +-
>>> block/bfq-iosched.c | 1 -
>>> block/blk-cgroup.c | 55 -
>>> block/blk-core.c | 1860 +-----------
>>> block/blk-exec.c | 20 +-
>>> block/blk-flush.c | 154 +-
>>> block/blk-ioc.c | 46 +-
>>> block/blk-merge.c | 35 +-
>>> block/blk-mq-debugfs.c | 2 -
>>> block/blk-mq-tag.c | 6 +-
>>> block/blk-mq.c | 13 +-
>>> block/blk-settings.c | 49 -
>>> block/blk-softirq.c | 20 -
>>> block/blk-sysfs.c | 39 +-
>>> block/blk-tag.c | 378 ---
>>> block/blk-timeout.c | 99 +-
>>> block/blk-wbt.c | 3 +-
>>> block/blk.h | 60 +-
>>> block/bsg-lib.c | 131 +-
>>> block/cfq-iosched.c | 4916
>>> --------------------------------
>>> block/deadline-iosched.c | 560 ----
>>> block/elevator.c | 447 +--
>>> block/kyber-iosched.c | 1 -
>>> block/mq-deadline.c | 1 -
>>> block/noop-iosched.c | 124 -
>>> drivers/block/sunvdc.c | 149 +-
>>> drivers/ide/ide-atapi.c | 25 +-
>>> drivers/ide/ide-cd.c | 175 +-
>>> drivers/ide/ide-disk.c | 5 +-
>>> drivers/ide/ide-io.c | 101 +-
>>> drivers/ide/ide-park.c | 4 +-
>>> drivers/ide/ide-pm.c | 28 +-
>>> drivers/ide/ide-probe.c | 68 +-
>>> drivers/infiniband/ulp/srp/ib_srp.c | 7 -
>>> drivers/md/Kconfig | 11 -
>>> drivers/md/dm-core.h | 10 -
>>> drivers/md/dm-mpath.c | 18 +-
>>> drivers/md/dm-rq.c | 293 +-
>>> drivers/md/dm-rq.h | 4 -
>>> drivers/md/dm-sysfs.c | 3 +-
>>> drivers/md/dm-table.c | 36 +-
>>> drivers/md/dm.c | 21 +-
>>> drivers/md/dm.h | 1 -
>>> drivers/memstick/core/ms_block.c | 110 +-
>>> drivers/memstick/core/ms_block.h | 1 +
>>> drivers/memstick/core/mspro_block.c | 121 +-
>>> drivers/s390/block/dasd_ioctl.c | 22 +-
>>> drivers/scsi/Kconfig | 12 -
>>> drivers/scsi/cxlflash/main.c | 6 -
>>> drivers/scsi/hosts.c | 29 +-
>>> drivers/scsi/lpfc/lpfc_scsi.c | 2 +-
>>> drivers/scsi/osd/osd_initiator.c | 4 +-
>>> drivers/scsi/osst.c | 2 +-
>>> drivers/scsi/qedi/qedi_main.c | 3 +-
>>> drivers/scsi/qla2xxx/qla_os.c | 30 +-
>>> drivers/scsi/scsi.c | 5 +-
>>> drivers/scsi/scsi_debug.c | 3 +-
>>> drivers/scsi/scsi_error.c | 4 +-
>>> drivers/scsi/scsi_lib.c | 624 +---
>>> drivers/scsi/scsi_priv.h | 1 -
>>> drivers/scsi/scsi_scan.c | 10 +-
>>> drivers/scsi/scsi_sysfs.c | 8 +-
>>> drivers/scsi/scsi_transport_fc.c | 72 +-
>>> drivers/scsi/scsi_transport_iscsi.c | 9 +-
>>> drivers/scsi/scsi_transport_sas.c | 10 +-
>>> drivers/scsi/sg.c | 2 +-
>>> drivers/scsi/st.c | 2 +-
>>> drivers/scsi/ufs/ufshcd.c | 6 -
>>> drivers/target/target_core_pscsi.c | 2 +-
>>> include/linux/blk-cgroup.h | 108 -
>>> include/linux/blkdev.h | 174 +-
>>> include/linux/bsg-lib.h | 3 +-
>>> include/linux/elevator.h | 90 +-
>>> include/linux/ide.h | 13 +-
>>> include/linux/init.h | 1 -
>>> include/scsi/scsi_host.h | 18 +-
>>> include/scsi/scsi_tcq.h | 14 +-
>>> init/do_mounts_initrd.c | 3 -
>>> init/initramfs.c | 6 -
>>> init/main.c | 12 -
>>> 85 files changed, 833 insertions(+), 11144 deletions(-)
>>
>> Hi Jens,
>>
>> Kernel oops[2] is triggered when running elevator switch stress test[1].
>>
>> [1] https://people.redhat.com/~minlei/tests/tools/elv-switch
>>
>> [2] kernel oops
>>
>> [ 399.702365] scsi 8:0:0:0: Direct-Access Linux scsi_debug
>> 0188 PQ: 0 ANSI: 7
>> [ 399.703603] sd 8:0:0:0: Power-on or device reset occurred
>> [ 399.709833] sd 8:0:0:0: [sdd] 16384 512-byte logical blocks: (8.39
>> MB/8.00 MiB)
>> [ 399.711745] sd 8:0:0:0: [sdd] Write Protect is off
>> [ 399.712395] sd 8:0:0:0: [sdd] Mode Sense: 73 00 10 08
>> [ 399.715119] sd 8:0:0:0: [sdd] Write cache: enabled, read cache: enabled,
>> supports DPO and FUA
>> [ 399.803561] sd 8:0:0:0: [sdd] Attached SCSI disk
>> [ 399.844825] sd 8:0:0:0: [sdd] Synchronizing SCSI cache
>> [ 399.968945] scsi 8:0:0:0: Direct-Access Linux scsi_debug
>> 0188 PQ: 0 ANSI: 7
>> [ 399.970077] sd 8:0:0:0: Power-on or device reset occurred
>> [ 399.972904] sd 8:0:0:0: [sdd] 16384 512-byte logical blocks: (8.39
>> MB/8.00 MiB)
>> [ 399.974823] sd 8:0:0:0: [sdd] Write Protect is off
>> [ 399.975411] sd 8:0:0:0: [sdd] Mode Sense: 73 00 10 08
>> [ 399.978052] sd 8:0:0:0: [sdd] Write cache: enabled, read cache: enabled,
>> supports DPO and FUA
>> [ 400.030588] BUG: unable to handle kernel NULL pointer dereference at
>> 0000000000000500
>> [ 400.032195] PGD 0 P4D 0
>> [ 400.032482] Oops: 0000 [#1] PREEMPT SMP PTI
>> [ 400.032945] CPU: 2 PID: 318 Comm: kworker/u8:5 Not tainted
>> 4.19.0_0ffdea6679a9_mq-conversions+ #1
>> [ 400.033927] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
>> 1.10.2-2.fc27 04/01/2014
>> [ 400.034915] Workqueue: events_unbound async_run_entry_fn
>> [ 400.035536] RIP: 0010:bfq_reset_rate_computation+0x52/0x85
>> [ 400.036177] Code: 00 48 89 83 b0 00 00 00 8b 45 20 c1 e8 09 89 83 d8 00
>> 00 00 48 89 83 d0 00 00 00 eb 0a c7 87 c8 00 00 00 00 00 00 00 48 8b 03 <48>
>> 8b b8 00 05 00 00 48 85 ff 74 24 8b 8b c8 00 00 00 4c 8b 8b d0
>> [ 400.038300] RSP: 0018:ffffc90000a47c50 EFLAGS: 00010046
>> [ 400.038915] RAX: 0000000000000000 RBX: ffff88017ac2bc00 RCX:
>> 0000000017d6067a
>> [ 400.039746] RDX: 0000000000000000 RSI: 0000000000000000 RDI:
>> ffff88017ac2bc00
>> [ 400.040573] RBP: ffff88017ac2bc00 R08: 00000000f461e6ac R09:
>> 0000000000000006
>> [ 400.041361] R10: 000000000000020f R11: 0000000000000000 R12:
>> ffff88016c130000
>> [ 400.042127] R13: 0000005d1c095013 R14: ffff88017ac2bf78 R15:
>> 0000000000000020
>> [ 400.042957] FS: 0000000000000000(0000) GS:ffff88017bb00000(0000)
>> knlGS:0000000000000000
>> [ 400.043895] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>> [ 400.044518] CR2: 0000000000000500 CR3: 0000000179c32004 CR4:
>> 0000000000760ee0
>> [ 400.045294] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
>> 0000000000000000
>> [ 400.046070] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
>> 0000000000000400
>> [ 400.046843] PKRU: 55555554
>> [ 400.047144] Call Trace:
>> [ 400.047438] bfq_finish_requeue_request+0x145/0x2fd
>> [ 400.047977] blk_mq_free_request+0x49/0xea
>> [ 400.048429] __scsi_execute+0x16c/0x17b
>> [ 400.048885] scsi_mode_sense+0x113/0x265
>> [ 400.049356] sd_revalidate_disk+0xb5b/0x109a [sd_mod]
>> [ 400.049947] ? __device_add_disk+0x3d2/0x3f6
>> [ 400.050415] sd_probe_async+0x10d/0x18b [sd_mod]
>> [ 400.050924] async_run_entry_fn+0x6d/0x12b
>> [ 400.051374] process_one_work+0x1da/0x313
>> [ 400.051841] ? rescuer_thread+0x282/0x282
>> [ 400.052313] worker_thread+0x1ca/0x295
>> [ 400.052769] kthread+0x115/0x11d
>> [ 400.053127] ? kthread_park+0x76/0x76
>> [ 400.053531] ret_from_fork+0x35/0x40
>> [ 400.053929] Modules linked in: scsi_debug null_blk isofs iTCO_wdt
>> iTCO_vendor_support i2c_i801 i2c_core lpc_ich mfd_core ip_tables sr_mod
>> cdrom usb_storage sd_mod ahci libahci crc32c_intel libata virtio_scsi
>> qemu_fw_cfg dm_mirror dm_region_hash dm_log dm_mod [last unloaded: null_blk]
>> [ 400.056640] Dumping ftrace buffer:
>> [ 400.057022] (ftrace buffer empty)
>> [ 400.057418] CR2: 0000000000000500
>> [ 400.057820] ---[ end trace 812cbc0fe8802fdd ]---
>
> Doesn't look related to the series, more like a bug in BFQ. Are you
> sure it passes on current -git? Or maybe the bug is exposed by the
> series.
>
> I'll try and reproduce it here and see what happens.
I think I see the error, it is introduced by my series. This incremental
should help, I'm going to test it now.
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index b8afdd6ec4b8..391128456aec 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -212,6 +212,21 @@ void exit_io_context(struct task_struct *task)
put_io_context_active(ioc);
}
+static void __ioc_clear_queue(struct list_head *icq_list)
+{
+ unsigned long flags;
+
+ while (!list_empty(icq_list)) {
+ struct io_cq *icq = list_entry(icq_list->next,
+ struct io_cq, q_node);
+ struct io_context *ioc = icq->ioc;
+
+ spin_lock_irqsave(&ioc->lock, flags);
+ ioc_destroy_icq(icq);
+ spin_unlock_irqrestore(&ioc->lock, flags);
+ }
+}
+
/**
* ioc_clear_queue - break any ioc association with the specified queue
* @q: request_queue being cleared
@@ -225,6 +240,8 @@ void ioc_clear_queue(struct request_queue *q)
spin_lock_irq(q->queue_lock);
list_splice_init(&q->icq_list, &icq_list);
spin_unlock_irq(q->queue_lock);
+
+ __ioc_clear_queue(&icq_list);
}
int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
--
Jens Axboe
