scsi: mpt3sas: Force request partial completion alignment

commit f2e767bb5d6ee0d988cb7d4e54b0b21175802b6b upstream.

The firmware or device, possibly under a heavy I/O load, can return on a
partial unaligned boundary. Scsi-ml expects these requests to be
completed on an alignment boundary. Scsi-ml blindly requeues the I/O
without checking the alignment boundary of the I/O request for the
remaining bytes. This leads to errors, since devices cannot perform
non-aligned read/write operations.

This patch fixes the issue in the driver. It aligns unaligned
completions of FS requests, by truncating them to the nearest alignment
boundary.

[mkp: simplified if statement]

Reported-by: Mauricio Faria De Oliveira <mauricfo@linux.vnet.ibm.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Acked-by: Sreekanth Reddy <Sreekanth.Reddy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: Ram Pai

drivers/scsi/mpt3sas/mpt3sas_scsih.c

@@ -4452,6 +4452,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
+	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 	scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
@@ -4510,6 +4511,20 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
+
+	/* In case of bogus fw or device, we could end up having
+	 * unaligned partial completion. We can force alignment here,
+	 * then scsi-ml does not need to handle this misbehavior.
+	 */
+	sector_sz = scmd->device->sector_size;
+	if (unlikely(scmd->request->cmd_type == REQ_TYPE_FS && sector_sz &&
+		     xfer_cnt % sector_sz)) {
+		sdev_printk(KERN_INFO, scmd->device,
+		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
+			    xfer_cnt, sector_sz);
+		xfer_cnt = round_down(xfer_cnt, sector_sz);
+	}
+
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);