Patchwork libata: Use Maximum Write Same Length to report discard size limit

login
register
mail settings
Submitter Martin K. Petersen
Date May 18, 2011, 2:13 a.m.
Message ID <yq1aaekhi2k.fsf@sermon.lab.mkp.net>
Download mbox | patch
Permalink /patch/96114/
State Not Applicable
Delegated to: David Miller
Headers show

Comments

Martin K. Petersen - May 18, 2011, 2:13 a.m.
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>

---

Jeff: This is an important fix for discard. I missed this patch when I
originally submitted the thin provisioning updates for 2.6.39.


--
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index e2f57e9e..30ea95f 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2138,7 +2138,7 @@  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]);
 	}