Linux SCSI subsystem development
 help / color / mirror / Atom feed
From: John Garry <john.g.garry@oracle.com>
To: Mike Christie <michael.christie@oracle.com>,
	bvanassche@acm.org, mwilck@suse.com, hch@lst.de,
	martin.petersen@oracle.com, linux-scsi@vger.kernel.org,
	james.bottomley@hansenpartnership.com
Subject: Re: [PATCH v10 07/33] scsi: sd: Have scsi-ml retry read_capacity_16 errors
Date: Mon, 17 Jul 2023 16:43:03 +0100	[thread overview]
Message-ID: <4c1252ca-0391-869a-2018-986e685f3611@oracle.com> (raw)
In-Reply-To: <20230714213419.95492-8-michael.christie@oracle.com>

On 14/07/2023 22:33, Mike Christie wrote:
> This has read_capacity_16 have scsi-ml retry errors instead of driving
> them itself.
> 
> There are 2 behavior changes with this patch:
> 1. There is one behavior change where we no longer retry when
> scsi_execute_cmd returns < 0, but we should be ok. We don't need to retry
> for failures like the queue being removed, and for the case where there
> are no tags/reqs since the block layer waits/retries for us. For possible
> memory allocation failures from blk_rq_map_kern we use GFP_NOIO, so
> retrying will probably not help.
> 2. For the specific UAs we checked for and retried, we would get
> READ_CAPACITY_RETRIES_ON_RESET retries plus whatever retries were left
> from the loop's retries. Each UA now gets READ_CAPACITY_RETRIES_ON_RESET
> reties, and the other errors (not including medium not present) get up
> to 3 retries.
> 
> Signed-off-by: Mike Christie <michael.christie@oracle.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Regardless of a couple of nitpicks, below:

Reviewed-by: John Garry <john.g.garry@oracle.com>

> ---
>   drivers/scsi/sd.c | 106 ++++++++++++++++++++++++++++++----------------
>   1 file changed, 69 insertions(+), 37 deletions(-)
> 
> diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
> index 755b09beff2a..245419fe9358 100644
> --- a/drivers/scsi/sd.c
> +++ b/drivers/scsi/sd.c
> @@ -2402,55 +2402,87 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
>   static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
>   						unsigned char *buffer)
>   {
> -	unsigned char cmd[16];
> +	static const u8 cmd[16] = { SERVICE_ACTION_IN_16, SAI_READ_CAPACITY_16,
> +				    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, RC16_LEN };

In terms of coding style, could you follow previous style, like:
	static const u8 cmd[16] = {
		[0] = SERVICE_ACTION_IN_16,
		[1] = SAI_READ_CAPACITY_16,
		[13] = RC16_LEN,
	};
	
Seems safe to me (to ensure we fill in the correct array element).

>   	struct scsi_sense_hdr sshdr;
> -	const struct scsi_exec_args exec_args = {
> -		.sshdr = &sshdr,
> -	};
>   	int sense_valid = 0;
>   	int the_result;
> -	int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET;
>   	unsigned int alignment;
>   	unsigned long long lba;
>   	unsigned sector_size;
> +	struct scsi_failure failures[] = {
> +		/*
> +		 * Fail immediately for Invalid Command Operation Code or
> +		 * Invalid Field in CDB.
> +		 */
> +		{
> +			.sense = ILLEGAL_REQUEST,
> +			.asc = 0x20,
> +			.allowed = 0,
> +			.result = SAM_STAT_CHECK_CONDITION,
> +		},
> +		{
> +			.sense = ILLEGAL_REQUEST,
> +			.asc = 0x24,
> +			.allowed = 0,
> +			.result = SAM_STAT_CHECK_CONDITION,
> +		},
> +		/* Fail immediately for Medium Not Present */
> +		{
> +			.sense = UNIT_ATTENTION,
> +			.asc = 0x3A,
> +			.allowed = 0,
> +			.result = SAM_STAT_CHECK_CONDITION,
> +		},
> +		{
> +			.sense = NOT_READY,
> +			.asc = 0x3A,
> +			.ascq = 0x0,
> +			.allowed = 0,
> +			.result = SAM_STAT_CHECK_CONDITION,
> +		},
> +		{
> +			.sense = UNIT_ATTENTION,
> +			.asc = 0x29,
> +			/* Device reset might occur several times */
> +			.allowed = READ_CAPACITY_RETRIES_ON_RESET,
> +			.result = SAM_STAT_CHECK_CONDITION,
> +		},
> +		/* Any other error not listed above retry */
> +		{
> +			.result = SCMD_FAILURE_RESULT_ANY,
> +			.allowed = 3,
> +		},
> +		{}
> +	};
> +	const struct scsi_exec_args exec_args = {
> +		.sshdr = &sshdr,
> +		.failures = failures,
> +	};
>   
>   	if (sdp->no_read_capacity_16)
>   		return -EINVAL;
>   
> -	do {
> -		memset(cmd, 0, 16);
> -		cmd[0] = SERVICE_ACTION_IN_16;
> -		cmd[1] = SAI_READ_CAPACITY_16;
> -		cmd[13] = RC16_LEN;
> -		memset(buffer, 0, RC16_LEN);
> -
> -		the_result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN,
> -					      buffer, RC16_LEN, SD_TIMEOUT,
> -					      sdkp->max_retries, &exec_args);
> -		if (the_result > 0) {
> -			if (media_not_present(sdkp, &sshdr))
> -				return -ENODEV;
> +	memset(buffer, 0, RC16_LEN);
>   
> -			sense_valid = scsi_sense_valid(&sshdr);
> -			if (sense_valid &&
> -			    sshdr.sense_key == ILLEGAL_REQUEST &&
> -			    (sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
> -			    sshdr.ascq == 0x00)
> -				/* Invalid Command Operation Code or
> -				 * Invalid Field in CDB, just retry
> -				 * silently with RC10 */
> -				return -EINVAL;
> -			if (sense_valid &&
> -			    sshdr.sense_key == UNIT_ATTENTION &&
> -			    sshdr.asc == 0x29 && sshdr.ascq == 0x00)
> -				/* Device reset might occur several times,
> -				 * give it one more chance */
> -				if (--reset_retries > 0)
> -					continue;
> -		}
> -		retries--;
> +	the_result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, buffer,
> +				      RC16_LEN, SD_TIMEOUT, sdkp->max_retries,
> +				      &exec_args);
>   
> -	} while (the_result && retries);
> +	if (the_result > 0) {
> +		if (media_not_present(sdkp, &sshdr))
> +			return -ENODEV;
> +
> +		sense_valid = scsi_sense_valid(&sshdr);
> +		if (sense_valid && sshdr.sense_key == ILLEGAL_REQUEST &&
> +		    (sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
> +		     sshdr.ascq == 0x00)
> +			/*
> +			 * Invalid Command Operation Code or Invalid Field in
> +			 * CDB, just retry silently with RC10
> +			 */
> +			return -EINVAL;


nit: personally I would use {} here, like below, but that's your choice.


  (sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
		     sshdr.ascq == 0x00) {
			/*
			 * Invalid Command Operation Code or Invalid Field in
			 * CDB, just retry silently with RC10
			 */
			return -EINVAL;
}

> +	}
>   
>   	if (the_result) {
>   		sd_print_result(sdkp, "Read Capacity(16) failed", the_result);


  reply	other threads:[~2023-07-17 15:43 UTC|newest]

Thread overview: 76+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-14 21:33 [PATCH v10 00/33] scsi: Allow scsi_execute users to control retries Mike Christie
2023-07-14 21:33 ` [PATCH v10 01/33] scsi: Add helper to prep sense during error handling Mike Christie
2023-07-17 15:24   ` John Garry
2023-07-14 21:33 ` [PATCH v10 02/33] scsi: Allow passthrough to override what errors to retry Mike Christie
2023-07-17 16:59   ` Bart Van Assche
2023-07-17 18:30     ` Mike Christie
2023-07-14 21:33 ` [PATCH v10 03/33] scsi: Add scsi_failure field to scsi_exec_args Mike Christie
2023-07-14 21:33 ` [PATCH v10 04/33] scsi: Have scsi-ml retry scsi_probe_lun errors Mike Christie
2023-07-19 18:33   ` Bart Van Assche
2023-07-14 21:33 ` [PATCH v10 05/33] scsi: retry INQUIRY after timeout Mike Christie
2023-07-14 21:33 ` [PATCH v10 06/33] scsi: sd: Fix sshdr use in read_capacity_16 Mike Christie
2023-07-17 15:26   ` John Garry
2023-07-19 18:34   ` Bart Van Assche
2023-07-14 21:33 ` [PATCH v10 07/33] scsi: sd: Have scsi-ml retry read_capacity_16 errors Mike Christie
2023-07-17 15:43   ` John Garry [this message]
2023-07-17 18:37     ` Mike Christie
2023-07-19 18:38   ` Bart Van Assche
2023-07-14 21:33 ` [PATCH v10 08/33] scsi: Use separate buf for START_STOP in sd_spinup_disk Mike Christie
2023-07-17 15:45   ` John Garry
2023-07-19 18:41     ` Bart Van Assche
2023-07-19 18:42   ` Bart Van Assche
2023-07-14 21:33 ` [PATCH v10 09/33] scsi: sd: Fix sshdr use " Mike Christie
2023-07-17 16:06   ` John Garry
2023-07-19 18:47   ` Bart Van Assche
2023-07-14 21:33 ` [PATCH v10 10/33] scsi: Have scsi-ml retry sd_spinup_disk errors Mike Christie
2023-07-19 19:53   ` Bart Van Assche
2023-07-14 21:33 ` [PATCH v10 11/33] scsi: hp_sw: Only access sshdr if res > 0 Mike Christie
2023-07-18 13:13   ` John Garry
2023-07-14 21:33 ` [PATCH v10 12/33] scsi: hp_sw: Have scsi-ml retry scsi_exec_req errors Mike Christie
2023-07-18 13:14   ` John Garry
2023-07-14 21:33 ` [PATCH v10 13/33] scsi: rdac: Fix sshdr use Mike Christie
2023-07-18 13:25   ` John Garry
2023-07-18 15:31     ` Mike Christie
2023-07-19 14:44       ` John Garry
2023-07-22 17:10         ` Mike Christie
2023-07-25  7:59           ` John Garry
2023-07-25 15:22             ` Mike Christie
2023-07-14 21:34 ` [PATCH v10 14/33] scsi: rdac: Have scsi-ml retry send_mode_select errors Mike Christie
2023-07-14 21:34 ` [PATCH v10 15/33] scsi: spi: Fix sshdr use Mike Christie
2023-07-18 16:53   ` John Garry
2023-07-14 21:34 ` [PATCH v10 16/33] scsi: spi: Have scsi-ml retry spi_execute errors Mike Christie
2023-07-19 14:43   ` John Garry
2023-07-14 21:34 ` [PATCH v10 17/33] scsi: sd: Fix sshdr use in sd_suspend_common Mike Christie
2023-07-25  9:59   ` John Garry
2023-07-14 21:34 ` [PATCH v10 18/33] scsi: sd: Have scsi-ml retry sd_sync_cache errors Mike Christie
2023-07-25 10:27   ` John Garry
2023-07-14 21:34 ` [PATCH v10 19/33] scsi: ch: Remove unit_attention Mike Christie
2023-07-25 10:30   ` John Garry
2023-07-14 21:34 ` [PATCH v10 20/33] scsi: ch: Have scsi-ml retry ch_do_scsi errors Mike Christie
2023-07-25 10:33   ` John Garry
2023-07-14 21:34 ` [PATCH v10 21/33] scsi: Have scsi-ml retry scsi_mode_sense UAs Mike Christie
2023-07-25 10:36   ` John Garry
2023-07-27  7:48   ` John Garry
2023-07-14 21:34 ` [PATCH v10 22/33] scsi: sd: Fix scsi_mode_sense caller's sshdr use Mike Christie
2023-07-27  7:57   ` John Garry
2023-07-31 18:14     ` michael.christie
2023-07-14 21:34 ` [PATCH v10 23/33] scsi: Have scsi-ml retry scsi_report_lun_scan errors Mike Christie
2023-07-27  8:00   ` John Garry
2023-07-14 21:34 ` [PATCH v10 24/33] scsi: sd: Have pr commands retry UAs Mike Christie
2023-07-14 21:34 ` [PATCH v10 25/33] scsi: sd: Have scsi-ml retry read_capacity_10 errors Mike Christie
2023-07-14 21:34 ` [PATCH v10 26/33] scsi: ses: Have scsi-ml retry scsi_exec_req errors Mike Christie
2023-07-14 21:34 ` [PATCH v10 27/33] scsi: sr: Have scsi-ml retry get_sectorsize errors Mike Christie
2023-07-14 21:34 ` [PATCH v10 28/33] scsi: ufs: Have scsi-ml retry start stop errors Mike Christie
2023-07-17 17:05   ` Bart Van Assche
2023-07-17 18:29     ` Mike Christie
2023-07-17 19:26       ` Bart Van Assche
2023-07-14 21:34 ` [PATCH v10 29/33] scsi: Fix sshdr use in scsi_test_unit_ready Mike Christie
2023-07-27  8:02   ` John Garry
2023-07-14 21:34 ` [PATCH v10 30/33] scsi: Fix sshdr use in scsi_cdl_enable Mike Christie
2023-07-27  8:03   ` John Garry
2023-07-14 21:34 ` [PATCH v10 31/33] scsi: sd: Fix sshdr use in cache_type_store Mike Christie
2023-07-27  8:04   ` John Garry
2023-07-14 21:34 ` [PATCH v10 32/33] scsi: sr: Fix sshdr use in sr_get_events Mike Christie
2023-07-27  8:06   ` John Garry
2023-07-14 21:34 ` [PATCH v10 33/33] scsi: Add kunit tests for scsi_check_passthrough Mike Christie
2023-07-17 16:21 ` [PATCH v10 00/33] scsi: Allow scsi_execute users to control retries Bart Van Assche

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=4c1252ca-0391-869a-2018-986e685f3611@oracle.com \
    --to=john.g.garry@oracle.com \
    --cc=bvanassche@acm.org \
    --cc=hch@lst.de \
    --cc=james.bottomley@hansenpartnership.com \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=michael.christie@oracle.com \
    --cc=mwilck@suse.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