From: Tom Yan <redacted>

As of commit 6b7e9cde4969 ("sd: Fix rw_max for devices that report
an optimal xfer size"), the scsi disk driver (correctly) derive both
of the queue limits "io_opt" and "max_sectors" from the optimal
transfer length field.

In case we would like the two limits to be derived from a value
other than BLK_DEF_MAX_SECTORS for ATA disks in the future, this
patch has made it easy.

Signed-off-by: Tom Yan <redacted>

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index bfec66f..ab75b5e 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c

@@ -2305,6 +2305,13 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 	put_unaligned_be16(min_io_sectors, &rbuf[6]);
 
 	/*
+	 * Optimal transfer length.
+	 *
+	 * This is used to derive the queue limit "max_sector" and "io_opt".
+	 */
+	put_unaligned_be32(BLK_DEF_MAX_SECTORS, &rbuf[12]);
+
+	/*
 	 * Optimal unmap granularity.
 	 *
 	 * The ATA spec doesn't even know about a granularity or alignment

-- 
2.9.0