scsi: mpt3sas: Swap I/O memory read value back to cpu endianness

Swap the I/O memory read value back to cpu endianness before storing it in
a data structures which are defined in the MPI headers where u8 components
are not defined in the endianness order.

In this area from day one mpt3sas driver is using le32_to_cpu() &
cpu_to_le32() APIs. But in commit cf6bf9710c
(mpt3sas: Bug fix for big endian systems) we have removed these APIs
before reading I/O memory which we should haven't done it. So
in this patch I am correcting it by adding these APIs back
before accessing I/O memory.

Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/mpt3sas/mpt3sas_base.c

@@ -3343,11 +3343,10 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 					spinlock_t *writeq_lock)
 {
 	unsigned long flags;
-	__u64 data_out = b;
 
 	spin_lock_irqsave(writeq_lock, flags);
-	writel((u32)(data_out), addr);
-	writel((u32)(data_out >> 32), (addr + 4));
+	__raw_writel((u32)(b), addr);
+	__raw_writel((u32)(b >> 32), (addr + 4));
 	mmiowb();
 	spin_unlock_irqrestore(writeq_lock, flags);
 }
@@ -3367,7 +3366,8 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 static inline void
 _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 {
-	writeq(b, addr);
+	__raw_writeq(b, addr);
+	mmiowb();
 }
 #else
 static inline void
@@ -5268,7 +5268,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 
 	/* send message 32-bits at a time */
 	for (i = 0, failed = 0; i < request_bytes/4 && !failed; i++) {
-		writel((u32)(request[i]), &ioc->chip->Doorbell);
+		writel(cpu_to_le32(request[i]), &ioc->chip->Doorbell);
 		if ((_base_wait_for_doorbell_ack(ioc, 5)))
 			failed = 1;
 	}
@@ -5289,7 +5289,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	}
 
 	/* read the first two 16-bits, it gives the total length of the reply */
-	reply[0] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[0] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 	if ((_base_wait_for_doorbell_int(ioc, 5))) {
@@ -5298,7 +5298,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 			ioc->name, __LINE__);
 		return -EFAULT;
 	}
-	reply[1] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[1] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 
@@ -5312,7 +5312,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 		if (i >=  reply_bytes/2) /* overflow case */
 			readl(&ioc->chip->Doorbell);
 		else
-			reply[i] = (u16)(readl(&ioc->chip->Doorbell)
+			reply[i] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 			    & MPI2_DOORBELL_DATA_MASK);
 		writel(0, &ioc->chip->HostInterruptStatus);
 	}