diff options
author | Bart Van Assche <bvanassche@acm.org> | 2022-08-16 10:26:38 -0700 |
---|---|---|
committer | Martin K. Petersen <martin.petersen@oracle.com> | 2022-08-22 22:45:25 -0400 |
commit | 785538bfdd682c8e962341d585f9b88262a0475e (patch) | |
tree | 13e80affbe33813b589f0aa1d99299cf8f88afb0 /drivers/scsi/sd.c | |
parent | fac8e558da9485e13a0ae0488aa0b8a8c307cd34 (diff) | |
download | linux-785538bfdd682c8e962341d585f9b88262a0475e.tar.bz2 |
scsi: sd: Revert "Rework asynchronous resume support"
Although commit 88f1669019bd ("scsi: sd: Rework asynchronous resume support")
eliminates a delay for some ATA disks after resume, it causes resume of ATA
disks to fail on other setups. See also:
* "Resume process hangs for 5-6 seconds starting sometime in 5.16"
(https://bugzilla.kernel.org/show_bug.cgi?id=215880).
* Geert's regression report
(https://lore.kernel.org/linux-scsi/alpine.DEB.2.22.394.2207191125130.1006766@ramsan.of.borg/).
This is what I understand about this issue:
* During resume, ata_port_pm_resume() starts the SCSI error handler. This
changes the SCSI host state into SHOST_RECOVERY and causes
scsi_queue_rq() to return BLK_STS_RESOURCE.
* sd_resume() calls sd_start_stop_device() for ATA devices. That function
in turn calls sd_submit_start() which tries to submit a START STOP UNIT
command. That command can only be submitted after the SCSI error handler
has changed the SCSI host state back to SHOST_RUNNING.
* The SCSI error handler runs on its own thread and calls
schedule_work(&(ap->scsi_rescan_task)). That causes
ata_scsi_dev_rescan() to be called from the context of a kernel
workqueue. That call hangs in blk_mq_get_tag(). I'm not sure why - maybe
because all available tags have been allocated by sd_submit_start()
calls (this is a guess).
Link: https://lore.kernel.org/r/20220816172638.538734-1-bvanassche@acm.org
Fixes: 88f1669019bd ("scsi: sd: Rework asynchronous resume support")
Cc: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: gzhqyz@gmail.com
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reported-by: gzhqyz@gmail.com
Reported-and-tested-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: John Garry <john.garry@huawei.com>
Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Diffstat (limited to 'drivers/scsi/sd.c')
-rw-r--r-- | drivers/scsi/sd.c | 84 |
1 files changed, 18 insertions, 66 deletions
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 8f79fa6318fe..eb76ba055021 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -103,7 +103,6 @@ static void sd_config_discard(struct scsi_disk *, unsigned int); static void sd_config_write_same(struct scsi_disk *); static int sd_revalidate_disk(struct gendisk *); static void sd_unlock_native_capacity(struct gendisk *disk); -static void sd_start_done_work(struct work_struct *work); static int sd_probe(struct device *); static int sd_remove(struct device *); static void sd_shutdown(struct device *); @@ -3471,7 +3470,6 @@ static int sd_probe(struct device *dev) sdkp->max_retries = SD_MAX_RETRIES; atomic_set(&sdkp->openers, 0); atomic_set(&sdkp->device->ioerr_cnt, 0); - INIT_WORK(&sdkp->start_done_work, sd_start_done_work); if (!sdp->request_queue->rq_timeout) { if (sdp->type != TYPE_MOD) @@ -3594,69 +3592,12 @@ static void scsi_disk_release(struct device *dev) kfree(sdkp); } -/* Process sense data after a START command finished. */ -static void sd_start_done_work(struct work_struct *work) -{ - struct scsi_disk *sdkp = container_of(work, typeof(*sdkp), - start_done_work); - struct scsi_sense_hdr sshdr; - int res = sdkp->start_result; - - if (res == 0) - return; - - sd_print_result(sdkp, "Start/Stop Unit failed", res); - - if (res < 0) - return; - - if (scsi_normalize_sense(sdkp->start_sense_buffer, - sdkp->start_sense_len, &sshdr)) - sd_print_sense_hdr(sdkp, &sshdr); -} - -/* A START command finished. May be called from interrupt context. */ -static void sd_start_done(struct request *req, blk_status_t status) -{ - const struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req); - struct scsi_disk *sdkp = scsi_disk(req->q->disk); - - sdkp->start_result = scmd->result; - WARN_ON_ONCE(scmd->sense_len > SCSI_SENSE_BUFFERSIZE); - sdkp->start_sense_len = scmd->sense_len; - memcpy(sdkp->start_sense_buffer, scmd->sense_buffer, - ARRAY_SIZE(sdkp->start_sense_buffer)); - WARN_ON_ONCE(!schedule_work(&sdkp->start_done_work)); -} - -/* Submit a START command asynchronously. */ -static int sd_submit_start(struct scsi_disk *sdkp, u8 cmd[], u8 cmd_len) -{ - struct scsi_device *sdev = sdkp->device; - struct request_queue *q = sdev->request_queue; - struct request *req; - struct scsi_cmnd *scmd; - - req = scsi_alloc_request(q, REQ_OP_DRV_IN, BLK_MQ_REQ_PM); - if (IS_ERR(req)) - return PTR_ERR(req); - - scmd = blk_mq_rq_to_pdu(req); - scmd->cmd_len = cmd_len; - memcpy(scmd->cmnd, cmd, cmd_len); - scmd->allowed = sdkp->max_retries; - req->timeout = SD_TIMEOUT; - req->rq_flags |= RQF_PM | RQF_QUIET; - req->end_io = sd_start_done; - blk_execute_rq_nowait(req, /*at_head=*/true); - - return 0; -} - static int sd_start_stop_device(struct scsi_disk *sdkp, int start) { unsigned char cmd[6] = { START_STOP }; /* START_VALID */ + struct scsi_sense_hdr sshdr; struct scsi_device *sdp = sdkp->device; + int res; if (start) cmd[4] |= 1; /* START */ @@ -3667,10 +3608,23 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) if (!scsi_device_online(sdp)) return -ENODEV; - /* Wait until processing of sense data has finished. */ - flush_work(&sdkp->start_done_work); + res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr, + SD_TIMEOUT, sdkp->max_retries, 0, RQF_PM, NULL); + if (res) { + sd_print_result(sdkp, "Start/Stop Unit failed", res); + if (res > 0 && scsi_sense_valid(&sshdr)) { + sd_print_sense_hdr(sdkp, &sshdr); + /* 0x3a is medium not present */ + if (sshdr.asc == 0x3a) + res = 0; + } + } - return sd_submit_start(sdkp, cmd, sizeof(cmd)); + /* SCSI error codes must not go to the generic layer */ + if (res) + return -EIO; + + return 0; } /* @@ -3697,8 +3651,6 @@ static void sd_shutdown(struct device *dev) sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); sd_start_stop_device(sdkp, 0); } - - flush_work(&sdkp->start_done_work); } static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) |