4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: James Bottomley <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>
commit ffb58456589443ca572221fabbdef3db8483a779 upstream.
mpt3sas has a firmware failure where it can only handle one pass through
ATA command at a time. If another comes in, contrary to the SAT
standard, it will hang until the first one completes (causing long
commands like secure erase to timeout). The original fix was to block
the device when an ATA command came in, but this caused a regression
with
commit 669f044170d8933c3d66d231b69ea97cb8447338
Author: Bart Van Assche <bart.vanassche@xxxxxxxxxxx>
Date: Tue Nov 22 16:17:13 2016 -0800
scsi: srp_transport: Move queuecommand() wait code to SCSI core
So fix the original fix of the secure erase timeout by properly
returning SAM_STAT_BUSY like the SAT recommends. The original patch
also had a concurrency problem since scsih_qcmd is lockless at that
point (this is fixed by using atomic bitops to set and test the flag).
[mkp: addressed feedback wrt. test_bit and fixed whitespace]
Fixes: 18f6084a989ba1b (mpt3sas: Fix secure erase premature termination)
Signed-off-by: James Bottomley <James.Bottomley@xxxxxxxxxxxxxxxxxxxxx>
Acked-by: Sreekanth Reddy <Sreekanth.Reddy@xxxxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reported-by: Ingo Molnar <mingo@xxxxxxxxxx>
Tested-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Cc: Joe Korty <joe.korty@xxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/scsi/mpt3sas/mpt3sas_base.h | 12 ++++++++++
drivers/scsi/mpt3sas/mpt3sas_scsih.c | 40 ++++++++++++++++++++++-------------
2 files changed, 38 insertions(+), 14 deletions(-)
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -390,6 +390,7 @@ struct MPT3SAS_TARGET {
* @eedp_enable: eedp support enable bit
* @eedp_type: 0(type_1), 1(type_2), 2(type_3)
* @eedp_block_length: block size
+ * @ata_command_pending: SATL passthrough outstanding for device
*/
struct MPT3SAS_DEVICE {
struct MPT3SAS_TARGET *sas_target;
@@ -398,6 +399,17 @@ struct MPT3SAS_DEVICE {
u8 configured_lun;
u8 block;
u8 tlr_snoop_check;
+ /*
+ * Bug workaround for SATL handling: the mpt2/3sas firmware
+ * doesn't return BUSY or TASK_SET_FULL for subsequent
+ * commands while a SATL pass through is in operation as the
+ * spec requires, it simply does nothing with them until the
+ * pass through completes, causing them possibly to timeout if
+ * the passthrough is a long executing command (like format or
+ * secure erase). This variable allows us to do the right
+ * thing while a SATL command is pending.
+ */
+ unsigned long ata_command_pending;
};
#define MPT3_CMD_NOT_USED 0x8000 /* free */
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3707,9 +3707,18 @@ _scsih_temp_threshold_events(struct MPT3
}
}
-static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd)
+static int _scsih_set_satl_pending(struct scsi_cmnd *scmd, bool pending)
{
- return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16);
+ struct MPT3SAS_DEVICE *priv = scmd->device->hostdata;
+
+ if (scmd->cmnd[0] != ATA_12 && scmd->cmnd[0] != ATA_16)
+ return 0;
+
+ if (pending)
+ return test_and_set_bit(0, &priv->ata_command_pending);
+
+ clear_bit(0, &priv->ata_command_pending);
+ return 0;
}
/**
@@ -3733,9 +3742,7 @@ _scsih_flush_running_cmds(struct MPT3SAS
if (!scmd)
continue;
count++;
- if (ata_12_16_cmd(scmd))
- scsi_internal_device_unblock(scmd->device,
- SDEV_RUNNING);
+ _scsih_set_satl_pending(scmd, false);
mpt3sas_base_free_smid(ioc, smid);
scsi_dma_unmap(scmd);
if (ioc->pci_error_recovery)
@@ -3866,13 +3873,6 @@ scsih_qcmd(struct Scsi_Host *shost, stru
if (ioc->logging_level & MPT_DEBUG_SCSI)
scsi_print_command(scmd);
- /*
- * Lock the device for any subsequent command until command is
- * done.
- */
- if (ata_12_16_cmd(scmd))
- scsi_internal_device_block(scmd->device);
-
sas_device_priv_data = scmd->device->hostdata;
if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
scmd->result = DID_NO_CONNECT << 16;
@@ -3886,6 +3886,19 @@ scsih_qcmd(struct Scsi_Host *shost, stru
return 0;
}
+ /*
+ * Bug work around for firmware SATL handling. The loop
+ * is based on atomic operations and ensures consistency
+ * since we're lockless at this point
+ */
+ do {
+ if (test_bit(0, &sas_device_priv_data->ata_command_pending)) {
+ scmd->result = SAM_STAT_BUSY;
+ scmd->scsi_done(scmd);
+ return 0;
+ }
+ } while (_scsih_set_satl_pending(scmd, true));
+
sas_target_priv_data = sas_device_priv_data->sas_target;
/* invalid device handle */
@@ -4445,8 +4458,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *i
if (scmd == NULL)
return 1;
- if (ata_12_16_cmd(scmd))
- scsi_internal_device_unblock(scmd->device, SDEV_RUNNING);
+ _scsih_set_satl_pending(scmd, false);
mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);