[SCSI] mpt2sas: Support for stopping driver when Firmware encounters

Added command line option and shost sysfs attribute called
mpt2sas_fwfault_debug. When enduser writes a "1" to this parameter, this
will enable support in the driver for debugging firmware timeout related
issues.  This handling was added in three areas (a) scsi error handling
callback called task_abort, (b) IOCTL interface, and (c) other timeouts that
result in diag resets, such as manufacturing config pages.  When this
support is enabled, the driver will provide dump_stack to console, halt
controller firmware, and panic driver. The end user probably would want to
setup serial console redirection so the dump stack can be seen.

Here are the three methods for enable this support:

(a) # insmod mpt2sas.ko mpt2sas_fwfault_debug=1
(b) # echo 1 > /sys/module/mpt2sas/parameters/mpt2sas_fwfault_debug
(c) # echo 1 > /sys/class/scsi_host/host#/fwfault_debug  (where # is
the host number)

Signed-off-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: Eric Moore <Eric.moore@lsi.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>

1 files changed, 74 insertions, 14 deletions

diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c
index 670241efa4b..617664cbf3f 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
@@ -77,6 +77,32 @@ static int msix_disable = -1;
 module_param(msix_disable, int, 0);
 MODULE_PARM_DESC(msix_disable, " disable msix routed interrupts (default=0)");
 
+int mpt2sas_fwfault_debug;
+MODULE_PARM_DESC(mpt2sas_fwfault_debug, " enable detection of firmware fault "
+    "and halt firmware - (default=0)");
+
+/**
+ * _scsih_set_fwfault_debug - global setting of ioc->fwfault_debug.
+ *
+ */
+static int
+_scsih_set_fwfault_debug(const char *val, struct kernel_param *kp)
+{
+        int ret = param_set_int(val, kp);
+        struct MPT2SAS_ADAPTER *ioc;
+
+        if (ret)
+                return ret;
+
+        printk(KERN_INFO "setting logging_level(0x%08x)\n",
+                                mpt2sas_fwfault_debug);
+        list_for_each_entry(ioc, &mpt2sas_ioc_list, list)
+                ioc->fwfault_debug = mpt2sas_fwfault_debug;
+        return 0;
+}
+module_param_call(mpt2sas_fwfault_debug, _scsih_set_fwfault_debug,
+    param_get_int, &mpt2sas_fwfault_debug, 0644);
+
 /**
  * _base_fault_reset_work - workq handling ioc fault conditions
  * @work: input argument, used to derive ioc
@@ -177,6 +203,51 @@ mpt2sas_base_stop_watchdog(struct MPT2SAS_ADAPTER *ioc)
         }
 }
 
+/**
+ * mpt2sas_base_fault_info - verbose translation of firmware FAULT code
+ * @ioc: per adapter object
+ * @fault_code: fault code
+ *
+ * Return nothing.
+ */
+void
+mpt2sas_base_fault_info(struct MPT2SAS_ADAPTER *ioc , u16 fault_code)
+{
+        printk(MPT2SAS_ERR_FMT "fault_state(0x%04x)!\n",
+            ioc->name, fault_code);
+}
+
+/**
+ * mpt2sas_halt_firmware - halt's mpt controller firmware
+ * @ioc: per adapter object
+ *
+ * For debugging timeout related issues.  Writing 0xCOFFEE00
+ * to the doorbell register will halt controller firmware. With
+ * the purpose to stop both driver and firmware, the enduser can
+ * obtain a ring buffer from controller UART.
+ */
+void
+mpt2sas_halt_firmware(struct MPT2SAS_ADAPTER *ioc)
+{
+        u32 doorbell;
+
+        if (!ioc->fwfault_debug)
+                return;
+
+        dump_stack();
+
+        doorbell = readl(&ioc->chip->Doorbell);
+        if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
+                mpt2sas_base_fault_info(ioc , doorbell);
+        else {
+                writel(0xC0FFEE00, &ioc->chip->Doorbell);
+                printk(MPT2SAS_ERR_FMT "Firmware is halted due to command "
+                    "timeout\n", ioc->name);
+        }
+
+        panic("panic in %s\n", __func__);
+}
+
 #ifdef CONFIG_SCSI_MPT2SAS_LOGGING
 /**
  * _base_sas_ioc_info - verbose translation of the ioc status
@@ -526,20 +597,6 @@ _base_sas_log_info(struct MPT2SAS_ADAPTER *ioc , u32 log_info)
 }
 
 /**
- * mpt2sas_base_fault_info - verbose translation of firmware FAULT code
- * @ioc: pointer to scsi command object
- * @fault_code: fault code
- *
- * Return nothing.
- */
-void
-mpt2sas_base_fault_info(struct MPT2SAS_ADAPTER *ioc , u16 fault_code)
-{
-        printk(MPT2SAS_ERR_FMT "fault_state(0x%04x)!\n",
-            ioc->name, fault_code);
-}
-
-/**
  * _base_display_reply_info -
  * @ioc: pointer to scsi command object
  * @smid: system request message index
@@ -3684,6 +3741,9 @@ mpt2sas_base_hard_reset_handler(struct MPT2SAS_ADAPTER *ioc, int sleep_flag,
         dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: enter\n", ioc->name,
             __func__));
 
+        if (mpt2sas_fwfault_debug)
+                mpt2sas_halt_firmware(ioc);
+
         spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
         if (ioc->shost_recovery) {
                 spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags);