hw/block/nvme: add the dataset management command

Add support for the Dataset Management command and the Deallocate
attribute. Deallocation results in discards being sent to the underlying
block device. Whether of not the blocks are actually deallocated is
affected by the same factors as Write Zeroes (see previous commit).

     format | discard | dsm (512B)  dsm (4KiB)  dsm (64KiB)
    --------------------------------------------------------
      qcow2    ignore   n           n           n
      qcow2    unmap    n           n           y
      raw      ignore   n           n           n
      raw      unmap    n           y           y

Again, a raw format and 4KiB LBAs are preferable.

In order to set the Namespace Preferred Deallocate Granularity and
Alignment fields (NPDG and NPDA), choose a sane minimum discard
granularity of 4KiB. If we are using a passthru device supporting
discard at a 512B granularity, user should set the discard_granularity
property explicitly. NPDG and NPDA will also account for the
cluster_size of the block driver if required (i.e. for QCOW2).

See NVM Express 1.3d, Section 6.7 ("Dataset Management command").

Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>

1 files changed, 26 insertions, 4 deletions

diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
index 53ded46034..37f95951a6 100644
--- a/hw/block/nvme-ns.c
+++ b/hw/block/nvme-ns.c
@@ -28,10 +28,14 @@
 #include "nvme.h"
 #include "nvme-ns.h"
 
-static void nvme_ns_init(NvmeNamespace *ns)
+#define MIN_DISCARD_GRANULARITY (4 * KiB)
+
+static int nvme_ns_init(NvmeNamespace *ns, Error **errp)
 {
+    BlockDriverInfo bdi;
     NvmeIdNs *id_ns = &ns->id_ns;
     int lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
+    int npdg;
 
     ns->id_ns.dlfeat = 0x9;
 
@@ -43,8 +47,19 @@ static void nvme_ns_init(NvmeNamespace *ns)
     id_ns->ncap = id_ns->nsze;
     id_ns->nuse = id_ns->ncap;
 
-    /* support DULBE */
-    id_ns->nsfeat |= 0x4;
+    /* support DULBE and I/O optimization fields */
+    id_ns->nsfeat |= (0x4 | 0x10);
+
+    npdg = ns->blkconf.discard_granularity / ns->blkconf.logical_block_size;
+
+    if (bdrv_get_info(blk_bs(ns->blkconf.blk), &bdi) >= 0 &&
+        bdi.cluster_size > ns->blkconf.discard_granularity) {
+        npdg = bdi.cluster_size / ns->blkconf.logical_block_size;
+    }
+
+    id_ns->npda = id_ns->npdg = npdg - 1;
+
+    return 0;
 }
 
 static int nvme_ns_init_blk(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
@@ -60,6 +75,11 @@ static int nvme_ns_init_blk(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
         return -1;
     }
 
+    if (ns->blkconf.discard_granularity == -1) {
+        ns->blkconf.discard_granularity =
+            MAX(ns->blkconf.logical_block_size, MIN_DISCARD_GRANULARITY);
+    }
+
     ns->size = blk_getlength(ns->blkconf.blk);
     if (ns->size < 0) {
         error_setg_errno(errp, -ns->size, "could not get blockdev size");
@@ -93,7 +113,9 @@ int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
         return -1;
     }
 
-    nvme_ns_init(ns);
+    if (nvme_ns_init(ns, errp)) {
+        return -1;
+    }
 
     if (nvme_register_namespace(n, ns, errp)) {
         return -1;