hw/block/nvme: conditionally enable DULBE for zoned namespaces

The device uses the BDRV_BLOCK_ZERO flag to determine the "deallocated"
status of logical blocks. Since the zoned namespaces command set
specification defines that logical blocks SHALL be marked as deallocated
when the zone is in the Empty or Offline states, DULBE can only be
supported if the zone size is a multiple of the calculated deallocation
granularity (reported in NPDG) which depends on the underlying block
device cluster size (if applicable) or the configured
discard_granularity.

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

diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
index 838b15c064f5ebc6647c930d2fdde8075d18e580..9be170abb78d8576dcc4d3550f359abd57be2087 100644 (file)
--- a/hw/block/nvme-ns.c
+++ b/hw/block/nvme-ns.c
@@ -16,6 +16,7 @@
 #include "qemu/units.h"
 #include "qemu/cutils.h"
 #include "qemu/log.h"
+#include "qemu/error-report.h"
 #include "hw/block/block.h"
 #include "hw/pci/pci.h"
 #include "sysemu/sysemu.h"
@@ -227,6 +228,22 @@ static void nvme_ns_init_zoned(NvmeCtrl *n, NvmeNamespace *ns, int lba_index)
     ns->id_ns.ncap = ns->id_ns.nsze;
     ns->id_ns.nuse = ns->id_ns.ncap;
 
+    /*
+     * The device uses the BDRV_BLOCK_ZERO flag to determine the "deallocated"
+     * status of logical blocks. Since the spec defines that logical blocks
+     * SHALL be deallocated when then zone is in the Empty or Offline states,
+     * we can only support DULBE if the zone size is a multiple of the
+     * calculated NPDG.
+     */
+    if (ns->zone_size % (ns->id_ns.npdg + 1)) {
+        warn_report("the zone size (%"PRIu64" blocks) is not a multiple of "
+                    "the calculated deallocation granularity (%d blocks); "
+                    "DULBE support disabled",
+                    ns->zone_size, ns->id_ns.npdg + 1);
+
+        ns->id_ns.nsfeat &= ~0x4;
+    }
+
     ns->id_ns_zoned = id_ns_z;
 }