libata: Use Maximum Write Same Length to report discard size limit
authorMartin K. Petersen <martin.petersen@oracle.com>
Wed, 18 May 2011 02:13:23 +0000 (22:13 -0400)
committerGreg Kroah-Hartman <gregkh@suse.de>
Fri, 3 Jun 2011 00:31:45 +0000 (09:31 +0900)
commit 5f4e206666f834340b69ddb43f86de3851c8675a upstream.

Previously we used Maximum Unmap LBA Count in the Block Limits VPD to
signal the maximum number of sectors we could handle in a single Write
Same command.

Starting with SBC3r26 the Block Limits VPD has an explicit limit on the
number of blocks in a Write Same. This means we can stop abusing a field
related to the Unmap command and let our SAT use the proper value in the
VPD (Maximum Write Same Length).

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
drivers/ata/libata-scsi.c

index dad2c95..d51f979 100644 (file)
@@ -2139,7 +2139,7 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
         * with the unmap bit set.
         */
        if (ata_id_has_trim(args->id)) {
-               put_unaligned_be32(65535 * 512 / 8, &rbuf[20]);
+               put_unaligned_be64(65535 * 512 / 8, &rbuf[36]);
                put_unaligned_be32(1, &rbuf[28]);
        }