From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hannes Reinecke Subject: [PATCHv3 1/6] scsi_error: count medium access timeout only once per EH run Date: Wed, 1 Mar 2017 10:15:15 +0100 Message-ID: <1488359720-130871-2-git-send-email-hare@suse.de> References: <1488359720-130871-1-git-send-email-hare@suse.de> Return-path: Received: from mx2.suse.de ([195.135.220.15]:55421 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752024AbdCAJep (ORCPT ); Wed, 1 Mar 2017 04:34:45 -0500 In-Reply-To: <1488359720-130871-1-git-send-email-hare@suse.de> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: "Martin K. Petersen" Cc: Christoph Hellwig , James Bottomley , Bart van Assche , linux-scsi@vger.kernel.org, Hannes Reinecke , Ewan Milne , Lawrence Obermann , Benjamin Block , Steffen Maier , Hannes Reinecke The current medium access timeout counter will be increased for each command, so if there are enough failed commands we'll hit the medium access timeout for even a single failure. Fix this by making the timeout per EH run, ie the counter will only be increased once per device and EH run. Cc: Ewan Milne Cc: Lawrence Obermann Cc: Benjamin Block Cc: Steffen Maier Signed-off-by: Hannes Reinecke --- drivers/scsi/scsi_error.c | 16 +++++++++++++++- drivers/scsi/sd.c | 21 +++++++++++++++++---- drivers/scsi/sd.h | 1 + include/scsi/scsi_driver.h | 2 +- 4 files changed, 34 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index f2cafae..cec439c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -58,6 +58,7 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd); static int scsi_try_to_abort_cmd(struct scsi_host_template *, struct scsi_cmnd *); +static int scsi_eh_reset(struct scsi_cmnd *scmd); /* called with shost->host_lock held */ void scsi_eh_wakeup(struct Scsi_Host *shost) @@ -249,6 +250,7 @@ int scsi_eh_scmd_add(struct scsi_cmnd *scmd, int eh_flag) if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) eh_flag &= ~SCSI_EH_CANCEL_CMD; scmd->eh_eflags |= eh_flag; + scsi_eh_reset(scmd); list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q); shost->host_failed++; scsi_eh_wakeup(shost); @@ -1107,7 +1109,19 @@ static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn) if (!blk_rq_is_passthrough(scmd->request)) { struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); if (sdrv->eh_action) - rtn = sdrv->eh_action(scmd, rtn); + rtn = sdrv->eh_action(scmd, rtn, false); + } + return rtn; +} + +static int scsi_eh_reset(struct scsi_cmnd *scmd) +{ + int rtn = SUCCESS; + + if (!blk_rq_is_passthrough(scmd->request)) { + struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); + if (sdrv->eh_action) + rtn = sdrv->eh_action(scmd, rtn, true); } return rtn; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index c7839f6..c794686 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -115,7 +115,7 @@ static int sd_init_command(struct scsi_cmnd *SCpnt); static void sd_uninit_command(struct scsi_cmnd *SCpnt); static int sd_done(struct scsi_cmnd *); -static int sd_eh_action(struct scsi_cmnd *, int); +static int sd_eh_action(struct scsi_cmnd *, int, bool); static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer); static void scsi_disk_release(struct device *cdev); static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *); @@ -1689,18 +1689,28 @@ static int sd_pr_clear(struct block_device *bdev, u64 key) * sd_eh_action - error handling callback * @scmd: sd-issued command that has failed * @eh_disp: The recovery disposition suggested by the midlayer + * @reset: Reset medium access counter * * This function is called by the SCSI midlayer upon completion of an * error test command (currently TEST UNIT READY). The result of sending * the eh command is passed in eh_disp. We're looking for devices that * fail medium access commands but are OK with non access commands like * test unit ready (so wrongly see the device as having a successful - * recovery) + * recovery). + * We have to be careful to count a medium access failure only once + * per SCSI EH run; there might be several timed out commands which + * will cause the 'max_medium_access_timeouts' counter to trigger + * after the first SCSI EH run already and set the device to offline. **/ -static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp) +static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp, bool reset) { struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk); + if (reset) { + /* New SCSI EH run, reset gate variable */ + sdkp->medium_access_reset = 0; + return eh_disp; + } if (!scsi_device_online(scmd->device) || !scsi_medium_access_command(scmd) || host_byte(scmd->result) != DID_TIME_OUT || @@ -1714,7 +1724,10 @@ static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp) * process of recovering or has it suffered an internal failure * that prevents access to the storage medium. */ - sdkp->medium_access_timed_out++; + if (!sdkp->medium_access_reset) { + sdkp->medium_access_timed_out++; + sdkp->medium_access_reset = 1; + } /* * If the device keeps failing read/write commands but TEST UNIT diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 4dac35e..6a4f75a 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -106,6 +106,7 @@ struct scsi_disk { unsigned rc_basis: 2; unsigned zoned: 2; unsigned urswrz : 1; + unsigned medium_access_reset : 1; }; #define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev) diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h index 891a658..d5e0012 100644 --- a/include/scsi/scsi_driver.h +++ b/include/scsi/scsi_driver.h @@ -15,7 +15,7 @@ struct scsi_driver { int (*init_command)(struct scsi_cmnd *); void (*uninit_command)(struct scsi_cmnd *); int (*done)(struct scsi_cmnd *); - int (*eh_action)(struct scsi_cmnd *, int); + int (*eh_action)(struct scsi_cmnd *, int, bool); }; #define to_scsi_driver(drv) \ container_of((drv), struct scsi_driver, gendrv) -- 1.8.5.6