On 5/11/18 2:12 PM, Tejun Heo wrote: > Hello, > > On Fri, May 11, 2018 at 12:51:02PM -0600, Jens Axboe wrote: >> Ever since we implemented NCQ for libata, the max queue depth on >> the device side has been limited to 31. This was done to retain one >> command for error handling. But we can utilize the full depth with >> a bit of fixing. > > This is great. Applied 1-9 to libata/for-4.18. Awesome, thanks! One piece of fallout, can you add the patch below as well? From: Jens Axboe <axboe@xxxxxxxxx> Subject: [PATCH] sata_fsl: use the right type for tag bitshift Since ATA_TAG_INTERNAL is now > 31 bits, we need to extend the type to ULL to cover 32/64-bit cases. Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 1b22d5c339d7..b8d9cfc60374 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1293,7 +1293,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); return; - } else if ((ap->qc_active & (1 << ATA_TAG_INTERNAL))) { + } else if ((ap->qc_active & (1ULL << ATA_TAG_INTERNAL))) { iowrite32(1, hcr_base + CC); qc = ata_qc_from_tag(ap, ATA_TAG_INTERNAL); -- Jens Axboe -- 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