This event occurs when dv sends an inquiry to a device,
and the device never returns, thus timing out.
This results in a task_abort, followed by host_reset.
>From host_reset, domain validation is invoked again, and this
loop repeats itself forever.
Invoking domain validation from host_reset is required, as
device go to slowest speed, asyn narrow.
The fix I propose is to keep a bitwise flag `hd->spi_pending`
that keeps track of the devices that are in progress of domain
validation. Then when host_reset occurs, we see if the
flag is non-zero, then take a different path which
program devices to old nego parameters, instead of calling dv
again. We do nothing for the device that currently in
the middle of dv. When `hd->spi_pending` is zero, then
dv is performed on all devices.
Please note, we tried using the starget_data->dv_pending flag
from host_reset, by calling dv for devices not pending,
and this doesn't work. The reason is if there is a faulty device
with a high id, such as 10, by the time we loop back to that id,
the dv_pending flag was always was zero, thus dv looped again.
Using the `hd->spi_pending` prevents nested dv, and at
the same time programs the devices back to previous nego.
Signed-off-by: Eric Moore <Eric.Moore@xxxxxxxx>
diff -uarpN b/drivers/message/fusion/mptbase.h a/drivers/message/fusion/mptbase.h
--- b/drivers/message/fusion/mptbase.h 2006-09-18 15:32:42.000000000 -0600
+++ a/drivers/message/fusion/mptbase.h 2006-09-18 16:07:46.000000000 -0600
@@ -981,6 +981,7 @@ typedef struct _MPT_SCSI_HOST {
int scandv_wait_done;
long last_queue_full;
u16 tm_iocstatus;
+ u16 spi_pending;
} MPT_SCSI_HOST;
/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
diff -uarpN b/drivers/message/fusion/mptspi.c a/drivers/message/fusion/mptspi.c
--- b/drivers/message/fusion/mptspi.c 2006-09-18 15:32:42.000000000 -0600
+++ a/drivers/message/fusion/mptspi.c 2006-09-18 16:07:09.000000000 -0600
@@ -302,7 +302,9 @@ static void mptspi_dv_device(struct _MPT
return;
}
+ hd->spi_pending |= (1 << sdev->id);
spi_dv_device(sdev);
+ hd->spi_pending &= ~(1 << sdev->id);
if (sdev->channel == 1 &&
mptscsih_quiesce_raid(hd, 0, vtarget->target_id) < 0)
@@ -789,11 +791,27 @@ mptspi_dv_renegotiate_work(void *data)
struct work_queue_wrapper *wqw = (struct work_queue_wrapper *)data;
struct _MPT_SCSI_HOST *hd = wqw->hd;
struct scsi_device *sdev;
+ struct scsi_target *starget;
+ struct _CONFIG_PAGE_SCSI_DEVICE_1 pg1;
+ u32 nego;
kfree(wqw);
- shost_for_each_device(sdev, hd->ioc->sh)
- mptspi_dv_device(hd, sdev);
+ if (hd->spi_pending) {
+ shost_for_each_device(sdev, hd->ioc->sh) {
+ if (hd->spi_pending & (1 << sdev->id))
+ continue;
+ starget = scsi_target(sdev);
+ nego = mptspi_getRP(starget);
+ pg1.RequestedParameters = cpu_to_le32(nego);
+ pg1.Reserved = 0;
+ pg1.Configuration = 0;
+ mptspi_write_spi_device_pg1(starget, &pg1);
+ }
+ } else {
+ shost_for_each_device(sdev, hd->ioc->sh)
+ mptspi_dv_device(hd, sdev);
+ }
}
static void
@@ -1054,6 +1072,7 @@ mptspi_probe(struct pci_dev *pdev, const
init_waitqueue_head(&hd->scandv_waitq);
hd->scandv_wait_done = 0;
hd->last_queue_full = 0;
+ hd->spi_pending = 0;
/* Some versions of the firmware don't support page 0; without
* that we can't get the parameters */
-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
