Re: [dm-devel] split scsi passthrough fields out of struct request V2

[Bart Van Assche <Bart.VanAssche@sandisk.com>]

On Tue, 2017-01-31 at 13:34 -0800, Bart Van Assche wrote:
> On Mon, 2017-01-30 at 17:38 -0800, Jens Axboe wrote:
> > That's a known bug in mainline. Pull it into 4.10-rc6,
> > or use my for-next where everything is already merged. 
> 
> Hello Jens,
> 
> With your for-next branch (commit c2e60b3a2602) I haven't hit any block
> layer crashes so far. The only issue I encountered that is new is a
> memory leak triggered by the SG-IO code. These memory leak reports
> started to appear after I started testing the mq-deadline scheduler.
> kmemleak reported the following call stack multiple times after my tests
> had finished:
> 
> unreferenced object 0xffff88041119e528 (size 192):
>   comm "multipathd", pid 2353, jiffies 4295128020 (age 1332.440s)
>   hex dump (first 32 bytes):
>     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>     00 00 00 00 00 00 00 00 12 01 00 00 00 00 00 00  ................
>   backtrace:
>     [<ffffffff8165e3b5>] kmemleak_alloc+0x45/0xa0
>     [<ffffffff811cc23d>] __kmalloc+0x15d/0x2f0
>     [<ffffffff81310e35>] bio_alloc_bioset+0x185/0x1f0
>     [<ffffffff813117f4>] bio_map_user_iov+0x124/0x400
>     [<ffffffff81320b7a>] blk_rq_map_user_iov+0x11a/0x210
>     [<ffffffff81320cbd>] blk_rq_map_user+0x4d/0x60
>     [<ffffffff81336694>] sg_io+0x3d4/0x410
>     [<ffffffff813369d0>] scsi_cmd_ioctl+0x300/0x490
>     [<ffffffff81336b9d>] scsi_cmd_blk_ioctl+0x3d/0x50
>     [<ffffffff814b4360>] sd_ioctl+0x80/0x100
>     [<ffffffff8132ddde>] blkdev_ioctl+0x51e/0x9f0
>     [<ffffffff8122f388>] block_ioctl+0x38/0x40
>     [<ffffffff8120097f>] do_vfs_ioctl+0x8f/0x700
>     [<ffffffff8120102c>] SyS_ioctl+0x3c/0x70
>     [<ffffffff8166c4aa>] entry_SYSCALL_64_fastpath+0x18/0xad

After I repeated my test the above findings were confirmed: no memory leaks
were reported by kmemleak after a test with I/O scheduler "none" and the
above call stack was reported 44 times by kmemleak after a test with I/O
scheduler "mq-deadline".

Bart.