[SCSI] ipr: fix eeh recovery for 64-bit adapters

In some scenarios, an EEH error can take a long time to be detected, since the
driver issues an MMIO read only after a device reset command times out and we
try to reset the adapter. This patch adds some code in ipr_cancel_op() to read
a hardware register so we detect the error earlier in case the op is being
aborted because of a timeout caused by a frozen adapter slot.

Another problem in such scenarios is that in __ipr_eh_host_reset() we change the
dump state flag from WAIT_FOR_DUMP to GET_DUMP, and the flag is later changed
from GET_DUMP to READ_DUMP in ipr_reset_restore_cfg_space(). However, if when
__ipr_eh_host_reset() is called by the SCSI error handling the function
ipr_reset_restore_cfg_space() has already been called by the PCI EEH code, we
end up with the flag in an inconsistent state. This patch also prevents this
problem.

Signed-off-by: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Acked-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>

diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 67b169b7a5be505e5e5935db55552d2bba13e7a0..b538f0883fd2e2314e76115936b606d38a79bc01 100644 (file)
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4613,11 +4613,13 @@ static int __ipr_eh_host_reset(struct scsi_cmnd * scsi_cmd)
        ENTER;
        ioa_cfg = (struct ipr_ioa_cfg *) scsi_cmd->device->host->hostdata;
 
-       dev_err(&ioa_cfg->pdev->dev,
-               "Adapter being reset as a result of error recovery.\n");
+       if (!ioa_cfg->in_reset_reload) {
+               dev_err(&ioa_cfg->pdev->dev,
+                       "Adapter being reset as a result of error recovery.\n");
 
-       if (WAIT_FOR_DUMP == ioa_cfg->sdt_state)
-               ioa_cfg->sdt_state = GET_DUMP;
+               if (WAIT_FOR_DUMP == ioa_cfg->sdt_state)
+                       ioa_cfg->sdt_state = GET_DUMP;
+       }
 
        rc = ipr_reset_reload(ioa_cfg, IPR_SHUTDOWN_ABBREV);
 
@@ -4907,7 +4909,7 @@ static int ipr_cancel_op(struct scsi_cmnd * scsi_cmd)
        struct ipr_ioa_cfg *ioa_cfg;
        struct ipr_resource_entry *res;
        struct ipr_cmd_pkt *cmd_pkt;
-       u32 ioasc;
+       u32 ioasc, int_reg;
        int op_found = 0;
 
        ENTER;
@@ -4920,7 +4922,17 @@ static int ipr_cancel_op(struct scsi_cmnd * scsi_cmd)
         */
        if (ioa_cfg->in_reset_reload || ioa_cfg->ioa_is_dead)
                return FAILED;
-       if (!res || !ipr_is_gscsi(res))
+       if (!res)
+               return FAILED;
+
+       /*
+        * If we are aborting a timed out op, chances are that the timeout was caused
+        * by a still not detected EEH error. In such cases, reading a register will
+        * trigger the EEH recovery infrastructure.
+        */
+       int_reg = readl(ioa_cfg->regs.sense_interrupt_reg);
+
+       if (!ipr_is_gscsi(res))
                return FAILED;
 
        list_for_each_entry(ipr_cmd, &ioa_cfg->pending_q, queue) {