On Sun, Mar 08, 2009 at 04:32:36PM -0500, James Bottomley wrote:
> Actually, found the reason, blk_rq_map_kern will blast the original bio
> from the request. You could fix this by chaining it back again at the
> beginning. If that works, we could just wrap it into a block API to
> prevent users from having to muck with bios.
How about constructing the TRIM entirely within libata? I won't be able
to test this patch until Oregon wakes up, but is this acceptable?
Advantages:
- Don't need to wait for T10 to finish designing UNMAP
- Uses well-tested ATA_16 passthrough layer
- Changing the UNMAP implementation to do multiple ranges won't break TRIM
- Will be easier to adapt to a future separation of scsi and libata
Disadvantages:
- UNMAP gets less testing
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index b9747fa..edcf9db 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1029,6 +1029,55 @@ static void ata_gen_ata_sense(struct ata_queued_cmd *qc)
desc[11] = block;
}
+static int ata_discard_fn(struct request_queue *q, struct request *req,
+ struct bio *bio)
+{
+ char *trim;
+ unsigned i, size;
+ struct page *page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+ /*
+ * Earlier, we set bi_size to the number of bytes to be discarded so
+ * that the elevators understood what was going on. The bi_size
+ * has been copied to req->data_len so we don't need to be
+ * concerned with that any more. Zero it out so it accurately
+ * reflects the length of the data we're now sending to the drive.
+ */
+ bio->bi_size = 0;
+
+ trim = bio_data(bio);
+ i = ata_set_lba_range_entries(trim, PAGE_SIZE / 8,
+ bio->bi_sector, bio_sectors(bio));
+ size = ALIGN(i * 8, 512);
+ memset(trim + i * 8, 0, size - i * 8);
+ if (bio_add_pc_page(q, bio, page, size, 0) < size) {
+ __free_page(page);
+ return -ENOMEM;
+ }
+
+ req->cmd_type = REQ_TYPE_BLOCK_PC;
+ req->cmd_len = 16;
+ req->cmd[0] = ATA_16;
+ req->cmd[1] = (ATA_PROT_DMA << 1) | 1; /* 48-bit, protocol */
+ req->cmd[2] = 0x6; /* length, direction */
+ req->cmd[3] = 0; /* feature high */
+ req->cmd[4] = ATA_DSM_TRIM; /* feature low */
+ req->cmd[5] = (size / 512) >> 8; /* nsect high */
+ req->cmd[6] = size / 512; /* nsect low */
+ req->cmd[7] = 0; /* lba */
+ req->cmd[8] = 0; /* lba */
+ req->cmd[9] = 0; /* lba */
+ req->cmd[10] = 0; /* lba */
+ req->cmd[11] = 0; /* lba */
+ req->cmd[12] = 0; /* lba */
+ req->cmd[13] = ATA_LBA; /* device */
+ req->cmd[14] = ATA_CMD_DSM; /* command */
+ req->cmd[15] = 0; /* control */
+
+ return 0;
+}
+
static void ata_scsi_sdev_config(struct scsi_device *sdev)
{
sdev->use_10_for_rw = 1;
@@ -1077,6 +1126,9 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
/* configure max sectors */
blk_queue_max_sectors(sdev->request_queue, dev->max_sectors);
+ if (ata_id_has_trim(dev->id))
+ blk_queue_set_discard(sdev->request_queue, ata_discard_fn);
+
if (dev->class == ATA_DEV_ATAPI) {
struct request_queue *q = sdev->request_queue;
void *buf;
@@ -2385,6 +2437,9 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf)
/* sector size */
rbuf[10] = ATA_SECT_SIZE >> 8;
rbuf[11] = ATA_SECT_SIZE & 0xff;
+
+ if (ata_id_has_trim(args->id))
+ rbuf[14] = 0x80;
}
return 0;
--
Matthew Wilcox Intel Open Source Technology Centre
"Bill, look, we understand that you're interested in selling us this
operating system, but compare it to ours. We can't possibly take such
a retrograde step."
--
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
