Re: [PATCH] qla4xxx: skip error recovery in case of register disconnect.

[Martin K. Petersen]

Manish,

> A system crashes when continuously removing/re-adding the storage
> controller.

Applied to 4.16/scsi-fixes. Thanks!

-- 
Martin K. Petersen  Oracle Linux Engineering

Re: [PATCH] qla4xxx: skip error recovery in case of register disconnect.

[Tomas Henzl]

On 02/12/2018 07:48 AM, Manish Rangankar wrote:
> A system crashes when continuously removing/re-adding
> the storage controller.
>
> Signed-off-by: Manish Rangankar 

Reviewed-by: Tomas Henzl 

Re: [PATCH] qla4xxx: skip error recovery in case of register disconnect.

[Ewan D. Milne]

On Sun, 2018-02-11 at 22:48 -0800, Manish Rangankar wrote:
> A system crashes when continuously removing/re-adding
> the storage controller.
> 
> Signed-off-by: Manish Rangankar 
> ---
>  drivers/scsi/qla4xxx/ql4_def.h |  2 ++
>  drivers/scsi/qla4xxx/ql4_os.c  | 46 
> ++
>  2 files changed, 48 insertions(+)
> 
> diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
> index fc23371..817f312 100644
> --- a/drivers/scsi/qla4xxx/ql4_def.h
> +++ b/drivers/scsi/qla4xxx/ql4_def.h
> @@ -168,6 +168,8 @@
>  #define DEV_DB_NON_PERSISTENT0
>  #define DEV_DB_PERSISTENT1
>  
> +#define QL4_ISP_REG_DISCONNECT 0xU
> +
>  #define COPY_ISID(dst_isid, src_isid) {  \
>   int i, j;   \
>   for (i = 0, j = ISID_SIZE - 1; i < ISID_SIZE;)  \
> diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
> index 2b8a8ce..efaa7f1 100644
> --- a/drivers/scsi/qla4xxx/ql4_os.c
> +++ b/drivers/scsi/qla4xxx/ql4_os.c
> @@ -262,6 +262,24 @@ static int qla4xxx_sysfs_ddb_logout(struct 
> iscsi_bus_flash_session *fnode_sess,
>  
>  static struct scsi_transport_template *qla4xxx_scsi_transport;
>  
> +static int qla4xxx_isp_check_reg(struct scsi_qla_host *ha)
> +{
> + u32 reg_val = 0;
> + int rval = QLA_SUCCESS;
> +
> + if (is_qla8022(ha))
> + reg_val = readl(&ha->qla4_82xx_reg->host_status);
> + else if (is_qla8032(ha) || is_qla8042(ha))
> + reg_val = qla4_8xxx_rd_direct(ha, QLA8XXX_PEG_ALIVE_COUNTER);
> + else
> + reg_val = readw(&ha->reg->ctrl_status);
> +
> + if (reg_val == QL4_ISP_REG_DISCONNECT)
> + rval = QLA_ERROR;
> +
> + return rval;
> +}
> +
>  static int qla4xxx_send_ping(struct Scsi_Host *shost, uint32_t iface_num,
>uint32_t iface_type, uint32_t payload_size,
>uint32_t pid, struct sockaddr *dst_addr)
> @@ -9188,10 +9206,17 @@ static int qla4xxx_eh_abort(struct scsi_cmnd *cmd)
>   struct srb *srb = NULL;
>   int ret = SUCCESS;
>   int wait = 0;
> + int rval;
>  
>   ql4_printk(KERN_INFO, ha, "scsi%ld:%d:%llu: Abort command issued 
> cmd=%p, cdb=0x%x\n",
>  ha->host_no, id, lun, cmd, cmd->cmnd[0]);
>  
> + rval = qla4xxx_isp_check_reg(ha);
> + if (rval != QLA_SUCCESS) {
> + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
> exiting.\n");
> + return FAILED;
> + }
> +
>   spin_lock_irqsave(&ha->hardware_lock, flags);
>   srb = (struct srb *) CMD_SP(cmd);
>   if (!srb) {
> @@ -9243,6 +9268,7 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd 
> *cmd)
>   struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
>   struct ddb_entry *ddb_entry = cmd->device->hostdata;
>   int ret = FAILED, stat;
> + int rval;
>  
>   if (!ddb_entry)
>   return ret;
> @@ -9262,6 +9288,12 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd 
> *cmd)
> cmd, jiffies, cmd->request->timeout / HZ,
> ha->dpc_flags, cmd->result, cmd->allowed));
>  
> + rval = qla4xxx_isp_check_reg(ha);
> + if (rval != QLA_SUCCESS) {
> + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
> exiting.\n");
> + return FAILED;
> + }
> +
>   /* FIXME: wait for hba to go online */
>   stat = qla4xxx_reset_lun(ha, ddb_entry, cmd->device->lun);
>   if (stat != QLA_SUCCESS) {
> @@ -9305,6 +9337,7 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd 
> *cmd)
>   struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
>   struct ddb_entry *ddb_entry = cmd->device->hostdata;
>   int stat, ret;
> + int rval;
>  
>   if (!ddb_entry)
>   return FAILED;
> @@ -9322,6 +9355,12 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd 
> *cmd)
> ha->host_no, cmd, jiffies, cmd->request->timeout / HZ,
> ha->dpc_flags, cmd->result, cmd->allowed));
>  
> + rval = qla4xxx_isp_check_reg(ha);
> + if (rval != QLA_SUCCESS) {
> + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
> exiting.\n");
> + return FAILED;
> + }
> +
>   stat = qla4xxx_reset_target(ha, ddb_entry);
>   if (stat != QLA_SUCCESS) {
>   starget_printk(KERN_INFO, scsi_target(cmd->device),
> @@ -9376,9 +9415,16 @@ static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd)
>  {
>   int return_status = FAILED;
>   struct scsi_qla_host *ha;
> + int rval;
>  
>   ha = to_qla_host(cmd->device->host);
>  
> + rval = qla4xxx_isp_check_reg(ha);
> + if (rval != QLA_SUCCESS) {
> + ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
> exiting.\n");
> + return FAILED;
> + }
> +
>   if ((is_qla8032(ha) || is_qla8042(ha)) && ql4xdontresethba)
>   qla4_83xx_set_

[PATCH] qla4xxx: skip error recovery in case of register disconnect.

[Manish Rangankar]

A system crashes when continuously removing/re-adding
the storage controller.

Signed-off-by: Manish Rangankar 
---
 drivers/scsi/qla4xxx/ql4_def.h |  2 ++
 drivers/scsi/qla4xxx/ql4_os.c  | 46 ++
 2 files changed, 48 insertions(+)

diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
index fc23371..817f312 100644
--- a/drivers/scsi/qla4xxx/ql4_def.h
+++ b/drivers/scsi/qla4xxx/ql4_def.h
@@ -168,6 +168,8 @@
 #define DEV_DB_NON_PERSISTENT  0
 #define DEV_DB_PERSISTENT  1
 
+#define QL4_ISP_REG_DISCONNECT 0xU
+
 #define COPY_ISID(dst_isid, src_isid) {\
int i, j;   \
for (i = 0, j = ISID_SIZE - 1; i < ISID_SIZE;)  \
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 2b8a8ce..efaa7f1 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -262,6 +262,24 @@ static int qla4xxx_sysfs_ddb_logout(struct 
iscsi_bus_flash_session *fnode_sess,
 
 static struct scsi_transport_template *qla4xxx_scsi_transport;
 
+static int qla4xxx_isp_check_reg(struct scsi_qla_host *ha)
+{
+   u32 reg_val = 0;
+   int rval = QLA_SUCCESS;
+
+   if (is_qla8022(ha))
+   reg_val = readl(&ha->qla4_82xx_reg->host_status);
+   else if (is_qla8032(ha) || is_qla8042(ha))
+   reg_val = qla4_8xxx_rd_direct(ha, QLA8XXX_PEG_ALIVE_COUNTER);
+   else
+   reg_val = readw(&ha->reg->ctrl_status);
+
+   if (reg_val == QL4_ISP_REG_DISCONNECT)
+   rval = QLA_ERROR;
+
+   return rval;
+}
+
 static int qla4xxx_send_ping(struct Scsi_Host *shost, uint32_t iface_num,
 uint32_t iface_type, uint32_t payload_size,
 uint32_t pid, struct sockaddr *dst_addr)
@@ -9188,10 +9206,17 @@ static int qla4xxx_eh_abort(struct scsi_cmnd *cmd)
struct srb *srb = NULL;
int ret = SUCCESS;
int wait = 0;
+   int rval;
 
ql4_printk(KERN_INFO, ha, "scsi%ld:%d:%llu: Abort command issued 
cmd=%p, cdb=0x%x\n",
   ha->host_no, id, lun, cmd, cmd->cmnd[0]);
 
+   rval = qla4xxx_isp_check_reg(ha);
+   if (rval != QLA_SUCCESS) {
+   ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
exiting.\n");
+   return FAILED;
+   }
+
spin_lock_irqsave(&ha->hardware_lock, flags);
srb = (struct srb *) CMD_SP(cmd);
if (!srb) {
@@ -9243,6 +9268,7 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd)
struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
struct ddb_entry *ddb_entry = cmd->device->hostdata;
int ret = FAILED, stat;
+   int rval;
 
if (!ddb_entry)
return ret;
@@ -9262,6 +9288,12 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd)
  cmd, jiffies, cmd->request->timeout / HZ,
  ha->dpc_flags, cmd->result, cmd->allowed));
 
+   rval = qla4xxx_isp_check_reg(ha);
+   if (rval != QLA_SUCCESS) {
+   ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
exiting.\n");
+   return FAILED;
+   }
+
/* FIXME: wait for hba to go online */
stat = qla4xxx_reset_lun(ha, ddb_entry, cmd->device->lun);
if (stat != QLA_SUCCESS) {
@@ -9305,6 +9337,7 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd)
struct scsi_qla_host *ha = to_qla_host(cmd->device->host);
struct ddb_entry *ddb_entry = cmd->device->hostdata;
int stat, ret;
+   int rval;
 
if (!ddb_entry)
return FAILED;
@@ -9322,6 +9355,12 @@ static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd)
  ha->host_no, cmd, jiffies, cmd->request->timeout / HZ,
  ha->dpc_flags, cmd->result, cmd->allowed));
 
+   rval = qla4xxx_isp_check_reg(ha);
+   if (rval != QLA_SUCCESS) {
+   ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
exiting.\n");
+   return FAILED;
+   }
+
stat = qla4xxx_reset_target(ha, ddb_entry);
if (stat != QLA_SUCCESS) {
starget_printk(KERN_INFO, scsi_target(cmd->device),
@@ -9376,9 +9415,16 @@ static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd)
 {
int return_status = FAILED;
struct scsi_qla_host *ha;
+   int rval;
 
ha = to_qla_host(cmd->device->host);
 
+   rval = qla4xxx_isp_check_reg(ha);
+   if (rval != QLA_SUCCESS) {
+   ql4_printk(KERN_INFO, ha, "PCI/Register disconnect, 
exiting.\n");
+   return FAILED;
+   }
+
if ((is_qla8032(ha) || is_qla8042(ha)) && ql4xdontresethba)
qla4_83xx_set_idc_dontreset(ha);
 
-- 
1.8.3.1