[SCSI] be2iscsi: Fix soft lock up issue during UE or if FW taking time to respond
The timeout set in MBX_CMD is 100sec and the ready bit checking in BMBX
mode is done for 4sec. After 4sec the task is scheduled out for 5 secs
to avoid kernel soft lockup stack trace. The loop of 4sec ready bit check
and then schedule out is done until the following conditon occur
- The Ready Bit is Set
- The timeout set in MBX_CMD expires
Signed-off-by: John Soni Jose <sony.john-n@emulex.com>
Signed-off-by: Jayamohan Kallickal <jayamohan.kallickal@emulex.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
diff --git a/drivers/scsi/be2iscsi/be.h b/drivers/scsi/be2iscsi/be.h
index 777e7c0..2e28f6c 100644
--- a/drivers/scsi/be2iscsi/be.h
+++ b/drivers/scsi/be2iscsi/be.h
@@ -128,7 +128,7 @@
#define PAGE_SHIFT_4K 12
#define PAGE_SIZE_4K (1 << PAGE_SHIFT_4K)
-#define mcc_timeout 120000 /* 5s timeout */
+#define mcc_timeout 120000 /* 12s timeout */
/* Returns number of pages spanned by the data starting at the given addr */
#define PAGES_4K_SPANNED(_address, size) \
diff --git a/drivers/scsi/be2iscsi/be_cmds.c b/drivers/scsi/be2iscsi/be_cmds.c
index f7788e5..df03067 100644
--- a/drivers/scsi/be2iscsi/be_cmds.c
+++ b/drivers/scsi/be2iscsi/be_cmds.c
@@ -490,33 +490,47 @@
**/
static int be_mbox_db_ready_wait(struct be_ctrl_info *ctrl)
{
+#define BEISCSI_MBX_RDY_BIT_TIMEOUT 4000 /* 4sec */
void __iomem *db = ctrl->db + MPU_MAILBOX_DB_OFFSET;
struct beiscsi_hba *phba = pci_get_drvdata(ctrl->pdev);
- uint32_t wait = 0;
+ unsigned long timeout;
+ bool read_flag = false;
+ int ret = 0, i;
u32 ready;
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(rdybit_check_q);
+
+ if (beiscsi_error(phba))
+ return -EIO;
+
+ timeout = jiffies + (HZ * 110);
do {
-
- if (beiscsi_error(phba))
- return -EIO;
-
- ready = ioread32(db) & MPU_MAILBOX_DB_RDY_MASK;
- if (ready)
- break;
-
- if (wait > BEISCSI_HOST_MBX_TIMEOUT) {
- beiscsi_log(phba, KERN_ERR,
- BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
- "BC_%d : FW Timed Out\n");
- phba->fw_timeout = true;
- beiscsi_ue_detect(phba);
- return -EBUSY;
+ for (i = 0; i < BEISCSI_MBX_RDY_BIT_TIMEOUT; i++) {
+ ready = ioread32(db) & MPU_MAILBOX_DB_RDY_MASK;
+ if (ready) {
+ read_flag = true;
+ break;
+ }
+ mdelay(1);
}
- mdelay(1);
- wait++;
- } while (true);
- return 0;
+ if (!read_flag) {
+ wait_event_timeout(rdybit_check_q,
+ (read_flag != true),
+ HZ * 5);
+ }
+ } while ((time_before(jiffies, timeout)) && !read_flag);
+
+ if (!read_flag) {
+ beiscsi_log(phba, KERN_ERR,
+ BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+ "BC_%d : FW Timed Out\n");
+ phba->fw_timeout = true;
+ beiscsi_ue_detect(phba);
+ ret = -EBUSY;
+ }
+
+ return ret;
}
/*
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 9918582..6ad36af 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -5002,14 +5002,13 @@
ret = beiscsi_cmd_reset_function(phba);
if (ret) {
beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
- "BM_%d : Reset Failed. Aborting Crashdump\n");
+ "BM_%d : Reset Failed\n");
goto hba_free;
}
ret = be_chk_reset_complete(phba);
if (ret) {
beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
- "BM_%d : Failed to get out of reset."
- "Aborting Crashdump\n");
+ "BM_%d : Failed to get out of reset.\n");
goto hba_free;
}