diff mbox series

[v6,06/11] hw/block/nvme: Introduce max active and open zone limits

Message ID 20201013214212.2152-7-dmitry.fomichev@wdc.com (mailing list archive)
State New, archived
Headers show
Series hw/block/nvme: Support Namespace Types and Zoned Namespace Command Set | expand

Commit Message

Dmitry Fomichev Oct. 13, 2020, 9:42 p.m. UTC 
Add two module properties, "max_active" and "max_open" to control
the maximum number of zones that can be active or open. Once these
variables are set to non-default values, these limits are checked
during I/O and Too Many Active or Too Many Open command status is
returned if they are exceeded.

Signed-off-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
---
 hw/block/nvme-ns.c | 28 ++++++++++++-
 hw/block/nvme-ns.h | 41 +++++++++++++++++++
 hw/block/nvme.c    | 99 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 166 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
index fedfad595c..8d9e11eef2 100644
--- a/hw/block/nvme-ns.c
+++ b/hw/block/nvme-ns.c
@@ -118,6 +118,20 @@  static int nvme_calc_zone_geometry(NvmeNamespace *ns, Error **errp)
         ns->zone_size_log2 = 63 - clz64(ns->zone_size);
     }
 
+    /* Make sure that the values of all ZNS properties are sane */
+    if (ns->params.max_open_zones > nz) {
+        error_setg(errp,
+                   "max_open_zones value %u exceeds the number of zones %u",
+                   ns->params.max_open_zones, nz);
+        return -1;
+    }
+    if (ns->params.max_active_zones > nz) {
+        error_setg(errp,
+                   "max_active_zones value %u exceeds the number of zones %u",
+                   ns->params.max_active_zones, nz);
+        return -1;
+    }
+
     return 0;
 }
 
@@ -172,8 +186,8 @@  static int nvme_zoned_init_ns(NvmeCtrl *n, NvmeNamespace *ns, int lba_index,
     id_ns_z = g_malloc0(sizeof(NvmeIdNsZoned));
 
     /* MAR/MOR are zeroes-based, 0xffffffff means no limit */
-    id_ns_z->mar = 0xffffffff;
-    id_ns_z->mor = 0xffffffff;
+    id_ns_z->mar = cpu_to_le32(ns->params.max_active_zones - 1);
+    id_ns_z->mor = cpu_to_le32(ns->params.max_open_zones - 1);
     id_ns_z->zoc = 0;
     id_ns_z->ozcs = ns->params.cross_zone_read ? 0x01 : 0x00;
 
@@ -199,6 +213,9 @@  static void nvme_zoned_clear_ns(NvmeNamespace *ns)
     uint32_t set_state;
     int i;
 
+    ns->nr_active_zones = 0;
+    ns->nr_open_zones = 0;
+
     zone = ns->zone_array;
     for (i = 0; i < ns->num_zones; i++, zone++) {
         switch (nvme_get_zone_state(zone)) {
@@ -209,6 +226,7 @@  static void nvme_zoned_clear_ns(NvmeNamespace *ns)
             QTAILQ_REMOVE(&ns->exp_open_zones, zone, entry);
             break;
         case NVME_ZONE_STATE_CLOSED:
+            nvme_aor_inc_active(ns);
             /* fall through */
         default:
             continue;
@@ -216,6 +234,9 @@  static void nvme_zoned_clear_ns(NvmeNamespace *ns)
 
         if (zone->d.wp == zone->d.zslba) {
             set_state = NVME_ZONE_STATE_EMPTY;
+        } else if (ns->params.max_active_zones == 0 ||
+                   ns->nr_active_zones < ns->params.max_active_zones) {
+            set_state = NVME_ZONE_STATE_CLOSED;
         } else {
             set_state = NVME_ZONE_STATE_CLOSED;
         }
@@ -224,6 +245,7 @@  static void nvme_zoned_clear_ns(NvmeNamespace *ns)
         case NVME_ZONE_STATE_CLOSED:
             trace_pci_nvme_clear_ns_close(nvme_get_zone_state(zone),
                                           zone->d.zslba);
+            nvme_aor_inc_active(ns);
             QTAILQ_INSERT_TAIL(&ns->closed_zones, zone, entry);
             break;
         case NVME_ZONE_STATE_EMPTY:
@@ -326,6 +348,8 @@  static Property nvme_ns_props[] = {
     DEFINE_PROP_SIZE("zone_capacity", NvmeNamespace, params.zone_cap_bs, 0),
     DEFINE_PROP_BOOL("cross_zone_read", NvmeNamespace,
                      params.cross_zone_read, false),
+    DEFINE_PROP_UINT32("max_active", NvmeNamespace, params.max_active_zones, 0),
+    DEFINE_PROP_UINT32("max_open", NvmeNamespace, params.max_open_zones, 0),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
index 170cbb8cdc..b0633d0def 100644
--- a/hw/block/nvme-ns.h
+++ b/hw/block/nvme-ns.h
@@ -34,6 +34,8 @@  typedef struct NvmeNamespaceParams {
     bool     cross_zone_read;
     uint64_t zone_size_bs;
     uint64_t zone_cap_bs;
+    uint32_t max_active_zones;
+    uint32_t max_open_zones;
 } NvmeNamespaceParams;
 
 typedef struct NvmeNamespace {
@@ -56,6 +58,8 @@  typedef struct NvmeNamespace {
     uint64_t        zone_capacity;
     uint64_t        zone_array_size;
     uint32_t        zone_size_log2;
+    int32_t         nr_open_zones;
+    int32_t         nr_active_zones;
 
     NvmeNamespaceParams params;
 } NvmeNamespace;
@@ -123,6 +127,43 @@  static inline bool nvme_wp_is_valid(NvmeZone *zone)
            st != NVME_ZONE_STATE_OFFLINE;
 }
 
+static inline void nvme_aor_inc_open(NvmeNamespace *ns)
+{
+    assert(ns->nr_open_zones >= 0);
+    if (ns->params.max_open_zones) {
+        ns->nr_open_zones++;
+        assert(ns->nr_open_zones <= ns->params.max_open_zones);
+    }
+}
+
+static inline void nvme_aor_dec_open(NvmeNamespace *ns)
+{
+    if (ns->params.max_open_zones) {
+        assert(ns->nr_open_zones > 0);
+        ns->nr_open_zones--;
+    }
+    assert(ns->nr_open_zones >= 0);
+}
+
+static inline void nvme_aor_inc_active(NvmeNamespace *ns)
+{
+    assert(ns->nr_active_zones >= 0);
+    if (ns->params.max_active_zones) {
+        ns->nr_active_zones++;
+        assert(ns->nr_active_zones <= ns->params.max_active_zones);
+    }
+}
+
+static inline void nvme_aor_dec_active(NvmeNamespace *ns)
+{
+    if (ns->params.max_active_zones) {
+        assert(ns->nr_active_zones > 0);
+        ns->nr_active_zones--;
+        assert(ns->nr_active_zones >= ns->nr_open_zones);
+    }
+    assert(ns->nr_active_zones >= 0);
+}
+
 int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp);
 void nvme_ns_drain(NvmeNamespace *ns);
 void nvme_ns_flush(NvmeNamespace *ns);
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 2e663713c7..088df2e813 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -199,6 +199,26 @@  static void nvme_assign_zone_state(NvmeNamespace *ns, NvmeZone *zone,
     }
 }
 
+/*
+ * Check if we can open a zone without exceeding open/active limits.
+ * AOR stands for "Active and Open Resources" (see TP 4053 section 2.5).
+ */
+static int nvme_aor_check(NvmeNamespace *ns, uint32_t act, uint32_t opn)
+{
+    if (ns->params.max_active_zones != 0 &&
+        ns->nr_active_zones + act > ns->params.max_active_zones) {
+        trace_pci_nvme_err_insuff_active_res(ns->params.max_active_zones);
+        return NVME_ZONE_TOO_MANY_ACTIVE | NVME_DNR;
+    }
+    if (ns->params.max_open_zones != 0 &&
+        ns->nr_open_zones + opn > ns->params.max_open_zones) {
+        trace_pci_nvme_err_insuff_open_res(ns->params.max_open_zones);
+        return NVME_ZONE_TOO_MANY_OPEN | NVME_DNR;
+    }
+
+    return NVME_SUCCESS;
+}
+
 static bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
 {
     hwaddr low = n->ctrl_mem.addr;
@@ -1207,6 +1227,41 @@  static uint16_t nvme_check_zone_read(NvmeNamespace *ns, NvmeZone *zone,
     return status;
 }
 
+static void nvme_auto_transition_zone(NvmeNamespace *ns, bool implicit,
+                                      bool adding_active)
+{
+    NvmeZone *zone;
+
+    if (implicit && ns->params.max_open_zones &&
+        ns->nr_open_zones == ns->params.max_open_zones) {
+        zone = QTAILQ_FIRST(&ns->imp_open_zones);
+        if (zone) {
+            /*
+             * Automatically close this implicitly open zone.
+             */
+            QTAILQ_REMOVE(&ns->imp_open_zones, zone, entry);
+            nvme_aor_dec_open(ns);
+            nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_CLOSED);
+        }
+    }
+}
+
+static uint16_t nvme_auto_open_zone(NvmeNamespace *ns, NvmeZone *zone)
+{
+    uint16_t status = NVME_SUCCESS;
+    uint8_t zs = nvme_get_zone_state(zone);
+
+    if (zs == NVME_ZONE_STATE_EMPTY) {
+        nvme_auto_transition_zone(ns, true, true);
+        status = nvme_aor_check(ns, 1, 1);
+    } else if (zs == NVME_ZONE_STATE_CLOSED) {
+        nvme_auto_transition_zone(ns, true, false);
+        status = nvme_aor_check(ns, 0, 1);
+    }
+
+    return status;
+}
+
 static bool nvme_finalize_zoned_write(NvmeNamespace *ns, NvmeRequest *req,
                                       bool failed)
 {
@@ -1243,7 +1298,11 @@  static bool nvme_finalize_zoned_write(NvmeNamespace *ns, NvmeRequest *req,
         switch (nvme_get_zone_state(zone)) {
         case NVME_ZONE_STATE_IMPLICITLY_OPEN:
         case NVME_ZONE_STATE_EXPLICITLY_OPEN:
+            nvme_aor_dec_open(ns);
+            /* fall through */
         case NVME_ZONE_STATE_CLOSED:
+            nvme_aor_dec_active(ns);
+            /* fall through */
         case NVME_ZONE_STATE_EMPTY:
             nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_FULL);
             /* fall through */
@@ -1272,7 +1331,10 @@  static uint64_t nvme_advance_zone_wp(NvmeNamespace *ns, NvmeZone *zone,
         zs = nvme_get_zone_state(zone);
         switch (zs) {
         case NVME_ZONE_STATE_EMPTY:
+            nvme_aor_inc_active(ns);
+            /* fall through */
         case NVME_ZONE_STATE_CLOSED:
+            nvme_aor_inc_open(ns);
             nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_IMPLICITLY_OPEN);
         }
     }
@@ -1378,6 +1440,11 @@  static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req)
             goto invalid;
         }
 
+        status = nvme_auto_open_zone(ns, zone);
+        if (status != NVME_SUCCESS) {
+            goto invalid;
+        }
+
         req->cqe.result64 = nvme_advance_zone_wp(ns, zone, nlb);
     }
 
@@ -1436,6 +1503,11 @@  static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req, bool append)
                 slba = zone->w_ptr;
             }
 
+            status = nvme_auto_open_zone(ns, zone);
+            if (status != NVME_SUCCESS) {
+                goto invalid;
+            }
+
             req->cqe.result64 = nvme_advance_zone_wp(ns, zone, nlb);
         } else {
             status = nvme_check_zone_read(ns, zone, slba, nlb, &rfc);
@@ -1537,9 +1609,27 @@  static uint16_t nvme_get_mgmt_zone_slba_idx(NvmeNamespace *ns, NvmeCmd *c,
 static uint16_t nvme_open_zone(NvmeNamespace *ns, NvmeZone *zone,
                                uint8_t state)
 {
+    uint16_t status;
+
     switch (state) {
     case NVME_ZONE_STATE_EMPTY:
+        nvme_auto_transition_zone(ns, false, true);
+        status = nvme_aor_check(ns, 1, 0);
+        if (status != NVME_SUCCESS) {
+            return status;
+        }
+        nvme_aor_inc_active(ns);
+        /* fall through */
     case NVME_ZONE_STATE_CLOSED:
+        status = nvme_aor_check(ns, 0, 1);
+        if (status != NVME_SUCCESS) {
+            if (state == NVME_ZONE_STATE_EMPTY) {
+                nvme_aor_dec_active(ns);
+            }
+            return status;
+        }
+        nvme_aor_inc_open(ns);
+        /* fall through */
     case NVME_ZONE_STATE_IMPLICITLY_OPEN:
         nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_EXPLICITLY_OPEN);
         /* fall through */
@@ -1561,6 +1651,7 @@  static uint16_t nvme_close_zone(NvmeNamespace *ns, NvmeZone *zone,
     switch (state) {
     case NVME_ZONE_STATE_EXPLICITLY_OPEN:
     case NVME_ZONE_STATE_IMPLICITLY_OPEN:
+        nvme_aor_dec_open(ns);
         nvme_assign_zone_state(ns, zone, NVME_ZONE_STATE_CLOSED);
         /* fall through */
     case NVME_ZONE_STATE_CLOSED:
@@ -1582,7 +1673,11 @@  static uint16_t nvme_finish_zone(NvmeNamespace *ns, NvmeZone *zone,
     switch (state) {
     case NVME_ZONE_STATE_EXPLICITLY_OPEN:
     case NVME_ZONE_STATE_IMPLICITLY_OPEN:
+        nvme_aor_dec_open(ns);
+        /* fall through */
     case NVME_ZONE_STATE_CLOSED:
+        nvme_aor_dec_active(ns);
+        /* fall through */
     case NVME_ZONE_STATE_EMPTY:
         zone->w_ptr = nvme_zone_wr_boundary(zone);
         zone->d.wp = zone->w_ptr;
@@ -1608,7 +1703,11 @@  static uint16_t nvme_reset_zone(NvmeNamespace *ns, NvmeZone *zone,
     switch (state) {
     case NVME_ZONE_STATE_EXPLICITLY_OPEN:
     case NVME_ZONE_STATE_IMPLICITLY_OPEN:
+        nvme_aor_dec_open(ns);
+        /* fall through */
     case NVME_ZONE_STATE_CLOSED:
+        nvme_aor_dec_active(ns);
+        /* fall through */
     case NVME_ZONE_STATE_FULL:
         zone->w_ptr = zone->d.zslba;
         zone->d.wp = zone->w_ptr;