From: Damien Le Moal <damien.lemoal@opensource.wdc.com>
To: John Garry <john.garry@huawei.com>,
linux-scsi@vger.kernel.org,
"Martin K . Petersen" <martin.petersen@oracle.com>,
Xiang Chen <chenxiang66@hisilicon.com>,
Jason Yan <yanaijie@huawei.com>
Subject: Re: [PATCH v3 27/31] scsi: pm8001: Cleanup pm8001_queue_command()
Date: Thu, 17 Feb 2022 20:47:29 +0900 [thread overview]
Message-ID: <eac105a1-4ce1-dcd3-38ba-088acbc9e85f@opensource.wdc.com> (raw)
In-Reply-To: <712a4702-8534-fad2-2679-cc5cf62e4a9e@huawei.com>
On 2/17/22 18:23, John Garry wrote:
> On 17/02/2022 00:12, Damien Le Moal wrote:
>>>>> I'll have a look at it. And that is on mainline or mkp-scsi staging, and
>>>>> not your patchset.
>>>> Are you saying that my patches suppresses the above ? This is submission
>>>> path and the dma code seems to complain about alignment... So bad buffer
>>>> addresses ?
>>> Your series does not suppress it. It doesn't occur often, so I need to
>>> check more.
>>>
>>> I think the issue is that we call dma_map_sg() twice, i.e. ccb never
>>> unmapped.
>> That would be a big issue indeed. We could add a flag to CCBs to track
>> the buf_prd DMA mapping state and BUG_ON() when ccb free function is
>> called with the buffer still mapped. That should allow catching this
>> infrequent problem ?
>>
>
> I figured out what is happening here and it does not help solve the
> mystery of my hang.
>
> Here's the steps:
> a. scsi_cmnd times out
> b. scsi error handling kicks in
> c. libsas attempts to abort the task, which fails
> d. libsas then tries IT nexus reset, which passes
> - libsas assumes the scsi_cmnd has completed with failure
> e. error handling concludes
> f. scsi midlayer then retries the same scsi_cmnd
> g. since we did not "free" associated ccb earlier or dma unmap at d.,
> the dma unmap on the same scsi_cmnd causes the warn
>
> So the LLD should really free resources and dma unmap at point IT nexus
> reset completes, but it doesn't. I think in certain conditions dma map
> should not be done twice.
>
> Anyway, that can be fixed, but I still have the hang :(
One thought: could it be bug with the DMA engine of your platform ?
What if you simply run an fio workload on the disk directly (no FS),
hang happens too ?
For the bugs I fixed with my series, it was the reverse: fio worked
great but everything broke down when I ran libzbc tests...
>
> Thanks,
> John
--
Damien Le Moal
Western Digital Research
next prev parent reply other threads:[~2022-02-17 11:47 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-14 2:17 [PATCH v3 00/31] libsas and pm8001 fixes Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 01/31] scsi: libsas: Fix sas_ata_qc_issue() handling of NCQ NON DATA commands Damien Le Moal
2022-02-14 17:56 ` John Garry
2022-02-14 22:23 ` Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 02/31] scsi: pm8001: Fix __iomem pointer use in pm8001_phy_control() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 03/31] scsi: pm8001: Fix pm8001_update_flash() local variable type Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 04/31] scsi: pm8001: Fix command initialization in pm80XX_send_read_log() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 05/31] scsi: pm8001: Fix pm80xx_pci_mem_copy() interface Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 06/31] scsi: pm8001: Fix command initialization in pm8001_chip_ssp_tm_req() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 07/31] scsi: pm8001: Fix payload initialization in pm80xx_set_thermal_config() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 08/31] scsi: pm8001: Fix le32 values handling in pm80xx_set_sas_protocol_timer_config() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 09/31] scsi: pm8001: Fix payload initialization in pm80xx_encrypt_update() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 10/31] scsi: pm8001: Fix le32 values handling in pm80xx_chip_ssp_io_req() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 11/31] scsi: pm8001: Fix le32 values handling in pm80xx_chip_sata_req() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 12/31] scsi: pm8001: Fix use of struct set_phy_profile_req fields Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 13/31] scsi: pm8001: Remove local variable in pm8001_pci_resume() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 14/31] scsi: pm8001: Fix NCQ NON DATA command task initialization Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 15/31] scsi: pm8001: Fix NCQ NON DATA command completion handling Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 16/31] scsi: pm8001: Fix abort all task initialization Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 17/31] scsi: pm8001: Fix pm8001_tag_alloc() failures handling Damien Le Moal
2022-02-14 18:02 ` John Garry
2022-02-14 2:17 ` [PATCH v3 18/31] scsi: pm8001: Fix pm80xx_chip_phy_ctl_req() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 19/31] scsi: pm8001: Fix pm8001_mpi_task_abort_resp() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 20/31] scsi: pm8001: Fix tag values handling Damien Le Moal
2022-02-15 11:09 ` John Garry
2022-02-15 23:44 ` Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 21/31] scsi: pm8001: Fix task leak in pm8001_send_abort_all() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 22/31] scsi: pm8001: Fix tag leaks on error Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 23/31] scsi: pm8001: fix memory leak in pm8001_chip_fw_flash_update_req() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 24/31] scsi: pm8001: Fix process_one_iomb() kdoc comment Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 25/31] scsi: libsas: Simplify sas_ata_qc_issue() detection of NCQ commands Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 26/31] scsi: pm8001: Simplify pm8001_get_ncq_tag() Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 27/31] scsi: pm8001: Cleanup pm8001_queue_command() Damien Le Moal
2022-02-15 10:55 ` John Garry
2022-02-16 11:36 ` Damien Le Moal
2022-02-16 11:38 ` John Garry
2022-02-16 11:42 ` Damien Le Moal
2022-02-16 11:50 ` John Garry
2022-02-16 12:05 ` Damien Le Moal
2022-02-16 12:21 ` John Garry
2022-02-17 0:12 ` Damien Le Moal
2022-02-17 9:23 ` John Garry
2022-02-17 10:47 ` Damien Le Moal
2022-02-17 12:49 ` John Garry
2022-02-18 3:12 ` Damien Le Moal
2022-02-18 11:21 ` John Garry
2022-02-17 11:47 ` Damien Le Moal [this message]
2022-02-14 2:17 ` [PATCH v3 28/31] scsi: pm8001: Introduce ccb alloc/free helpers Damien Le Moal
2022-02-15 11:07 ` John Garry
2022-02-15 23:41 ` Damien Le Moal
2022-02-16 11:43 ` Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 29/31] scsi: pm8001: Simplify pm8001_mpi_build_cmd() interface Damien Le Moal
2022-02-14 2:17 ` [PATCH v3 30/31] scsi: pm8001: Simplify pm8001_task_exec() Damien Le Moal
2022-02-15 8:57 ` John Garry
2022-02-14 2:17 ` [PATCH v3 31/31] scsi: pm8001: Simplify pm8001_ccb_task_free() Damien Le Moal
2022-02-14 2:23 ` [PATCH v3 00/31] libsas and pm8001 fixes Damien Le Moal
2022-02-15 3:18 ` Martin K. Petersen
2022-02-15 7:38 ` Damien Le Moal
2022-02-14 18:06 ` John Garry
2022-02-14 22:29 ` Damien Le Moal
2022-02-15 8:16 ` John Garry
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=eac105a1-4ce1-dcd3-38ba-088acbc9e85f@opensource.wdc.com \
--to=damien.lemoal@opensource.wdc.com \
--cc=chenxiang66@hisilicon.com \
--cc=john.garry@huawei.com \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=yanaijie@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox