hw/block/nvme: support the get/set features select and save fields

Since the device does not have any persistent state storage, no
features are "saveable" and setting the Save (SV) field in any Set
Features command will result in a Feature Identifier Not Saveable status
code.

Similarly, if the Select (SEL) field is set to request saved values, the
devices will (as it should) return the default values instead.

Since this also introduces "Supported Capabilities", the nsid field is
now also checked for validity wrt. the feature being get/set'ed.

Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20200706061303.246057-13-its@irrelevant.dk>

3 files changed, 119 insertions, 15 deletions

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 889a52ba11..bfc23037c3 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -99,6 +99,14 @@ static const bool nvme_feature_support[NVME_FID_MAX] = {
     [NVME_TIMESTAMP]                = true,
 };
 
+static const uint32_t nvme_feature_cap[NVME_FID_MAX] = {
+    [NVME_TEMPERATURE_THRESHOLD]    = NVME_FEAT_CAP_CHANGE,
+    [NVME_VOLATILE_WRITE_CACHE]     = NVME_FEAT_CAP_CHANGE,
+    [NVME_NUMBER_OF_QUEUES]         = NVME_FEAT_CAP_CHANGE,
+    [NVME_ASYNCHRONOUS_EVENT_CONF]  = NVME_FEAT_CAP_CHANGE,
+    [NVME_TIMESTAMP]                = NVME_FEAT_CAP_CHANGE,
+};
+
 static void nvme_process_sq(void *opaque);
 
 static uint16_t nvme_cid(NvmeRequest *req)
@@ -1098,20 +1106,47 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
     uint32_t dw10 = le32_to_cpu(cmd->cdw10);
     uint32_t dw11 = le32_to_cpu(cmd->cdw11);
+    uint32_t nsid = le32_to_cpu(cmd->nsid);
     uint32_t result;
     uint8_t fid = NVME_GETSETFEAT_FID(dw10);
+    NvmeGetFeatureSelect sel = NVME_GETFEAT_SELECT(dw10);
     uint16_t iv;
 
     static const uint32_t nvme_feature_default[NVME_FID_MAX] = {
         [NVME_ARBITRATION] = NVME_ARB_AB_NOLIMIT,
     };
 
-    trace_pci_nvme_getfeat(nvme_cid(req), fid, dw11);
+    trace_pci_nvme_getfeat(nvme_cid(req), fid, sel, dw11);
 
     if (!nvme_feature_support[fid]) {
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
+    if (nvme_feature_cap[fid] & NVME_FEAT_CAP_NS) {
+        if (!nsid || nsid > n->num_namespaces) {
+            /*
+             * The Reservation Notification Mask and Reservation Persistence
+             * features require a status code of Invalid Field in Command when
+             * NSID is 0xFFFFFFFF. Since the device does not support those
+             * features we can always return Invalid Namespace or Format as we
+             * should do for all other features.
+             */
+            return NVME_INVALID_NSID | NVME_DNR;
+        }
+    }
+
+    switch (sel) {
+    case NVME_GETFEAT_SELECT_CURRENT:
+        break;
+    case NVME_GETFEAT_SELECT_SAVED:
+        /* no features are saveable by the controller; fallthrough */
+    case NVME_GETFEAT_SELECT_DEFAULT:
+        goto defaults;
+    case NVME_GETFEAT_SELECT_CAP:
+        result = nvme_feature_cap[fid];
+        goto out;
+    }
+
     switch (fid) {
     case NVME_TEMPERATURE_THRESHOLD:
         result = 0;
@@ -1121,22 +1156,45 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
          * return 0 for all other sensors.
          */
         if (NVME_TEMP_TMPSEL(dw11) != NVME_TEMP_TMPSEL_COMPOSITE) {
-            break;
+            goto out;
         }
 
         switch (NVME_TEMP_THSEL(dw11)) {
         case NVME_TEMP_THSEL_OVER:
             result = n->features.temp_thresh_hi;
-            break;
+            goto out;
         case NVME_TEMP_THSEL_UNDER:
             result = n->features.temp_thresh_low;
-            break;
+            goto out;
         }
 
-        break;
+        return NVME_INVALID_FIELD | NVME_DNR;
     case NVME_VOLATILE_WRITE_CACHE:
         result = blk_enable_write_cache(n->conf.blk);
         trace_pci_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
+        goto out;
+    case NVME_ASYNCHRONOUS_EVENT_CONF:
+        result = n->features.async_config;
+        goto out;
+    case NVME_TIMESTAMP:
+        return nvme_get_feature_timestamp(n, cmd);
+    default:
+        break;
+    }
+
+defaults:
+    switch (fid) {
+    case NVME_TEMPERATURE_THRESHOLD:
+        result = 0;
+
+        if (NVME_TEMP_TMPSEL(dw11) != NVME_TEMP_TMPSEL_COMPOSITE) {
+            break;
+        }
+
+        if (NVME_TEMP_THSEL(dw11) == NVME_TEMP_THSEL_OVER) {
+            result = NVME_TEMPERATURE_WARNING;
+        }
+
         break;
     case NVME_NUMBER_OF_QUEUES:
         result = (n->params.max_ioqpairs - 1) |
@@ -1155,16 +1213,12 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         }
 
         break;
-    case NVME_ASYNCHRONOUS_EVENT_CONF:
-        result = n->features.async_config;
-        break;
-    case NVME_TIMESTAMP:
-        return nvme_get_feature_timestamp(n, cmd);
     default:
         result = nvme_feature_default[fid];
         break;
     }
 
+out:
     req->cqe.result = cpu_to_le32(result);
     return NVME_SUCCESS;
 }
@@ -1191,14 +1245,37 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
     uint32_t dw10 = le32_to_cpu(cmd->cdw10);
     uint32_t dw11 = le32_to_cpu(cmd->cdw11);
+    uint32_t nsid = le32_to_cpu(cmd->nsid);
     uint8_t fid = NVME_GETSETFEAT_FID(dw10);
+    uint8_t save = NVME_SETFEAT_SAVE(dw10);
+
+    trace_pci_nvme_setfeat(nvme_cid(req), fid, save, dw11);
 
-    trace_pci_nvme_setfeat(nvme_cid(req), fid, dw11);
+    if (save) {
+        return NVME_FID_NOT_SAVEABLE | NVME_DNR;
+    }
 
     if (!nvme_feature_support[fid]) {
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
+    if (nvme_feature_cap[fid] & NVME_FEAT_CAP_NS) {
+        if (!nsid || (nsid != NVME_NSID_BROADCAST &&
+                      nsid > n->num_namespaces)) {
+            return NVME_INVALID_NSID | NVME_DNR;
+        }
+    } else if (nsid && nsid != NVME_NSID_BROADCAST) {
+        if (nsid > n->num_namespaces) {
+            return NVME_INVALID_NSID | NVME_DNR;
+        }
+
+        return NVME_FEAT_NOT_NS_SPEC | NVME_DNR;
+    }
+
+    if (!(nvme_feature_cap[fid] & NVME_FEAT_CAP_CHANGE)) {
+        return NVME_FEAT_NOT_CHANGEABLE | NVME_DNR;
+    }
+
     switch (fid) {
     case NVME_TEMPERATURE_THRESHOLD:
         if (NVME_TEMP_TMPSEL(dw11) != NVME_TEMP_TMPSEL_COMPOSITE) {
@@ -2055,7 +2132,9 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
     id->sqes = (0x6 << 4) | 0x6;
     id->cqes = (0x4 << 4) | 0x4;
     id->nn = cpu_to_le32(n->num_namespaces);
-    id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP);
+    id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP |
+                           NVME_ONCS_FEATURES);
+
     id->psd[0].mp = cpu_to_le16(0x9c4);
     id->psd[0].enlat = cpu_to_le32(0x10);
     id->psd[0].exlat = cpu_to_le32(0x4);
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 42e62f4649..4a4ef34071 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -46,8 +46,8 @@ pci_nvme_identify_ctrl(void) "identify controller"
 pci_nvme_identify_ns(uint32_t ns) "nsid %"PRIu32""
 pci_nvme_identify_nslist(uint32_t ns) "nsid %"PRIu32""
 pci_nvme_get_log(uint16_t cid, uint8_t lid, uint8_t lsp, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx8" lsp 0x%"PRIx8" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
-pci_nvme_getfeat(uint16_t cid, uint8_t fid, uint32_t cdw11) "cid %"PRIu16" fid 0x%"PRIx8" cdw11 0x%"PRIx32""
-pci_nvme_setfeat(uint16_t cid, uint8_t fid, uint32_t cdw11) "cid %"PRIu16" fid 0x%"PRIx8" cdw11 0x%"PRIx32""
+pci_nvme_getfeat(uint16_t cid, uint8_t fid, uint8_t sel, uint32_t cdw11) "cid %"PRIu16" fid 0x%"PRIx8" sel 0x%"PRIx8" cdw11 0x%"PRIx32""
+pci_nvme_setfeat(uint16_t cid, uint8_t fid, uint8_t save, uint32_t cdw11) "cid %"PRIu16" fid 0x%"PRIx8" save 0x%"PRIx8" cdw11 0x%"PRIx32""
 pci_nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s"
 pci_nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
 pci_nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 64d2cab782..370df7fc05 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -664,7 +664,7 @@ enum NvmeStatusCodes {
     NVME_INVALID_QUEUE_DEL      = 0x010c,
     NVME_FID_NOT_SAVEABLE       = 0x010d,
     NVME_FEAT_NOT_CHANGEABLE    = 0x010e,
-    NVME_FID_NOT_NSID_SPEC      = 0x010f,
+    NVME_FEAT_NOT_NS_SPEC       = 0x010f,
     NVME_FW_REQ_SUSYSTEM_RESET  = 0x0110,
     NVME_CONFLICTING_ATTRS      = 0x0180,
     NVME_INVALID_PROT_INFO      = 0x0181,
@@ -908,9 +908,32 @@ enum NvmeFeatureIds {
     NVME_FID_MAX                    = 0x100,
 };
 
+typedef enum NvmeFeatureCap {
+    NVME_FEAT_CAP_SAVE      = 1 << 0,
+    NVME_FEAT_CAP_NS        = 1 << 1,
+    NVME_FEAT_CAP_CHANGE    = 1 << 2,
+} NvmeFeatureCap;
+
+typedef enum NvmeGetFeatureSelect {
+    NVME_GETFEAT_SELECT_CURRENT = 0x0,
+    NVME_GETFEAT_SELECT_DEFAULT = 0x1,
+    NVME_GETFEAT_SELECT_SAVED   = 0x2,
+    NVME_GETFEAT_SELECT_CAP     = 0x3,
+} NvmeGetFeatureSelect;
+
 #define NVME_GETSETFEAT_FID_MASK 0xff
 #define NVME_GETSETFEAT_FID(dw10) (dw10 & NVME_GETSETFEAT_FID_MASK)
 
+#define NVME_GETFEAT_SELECT_SHIFT 8
+#define NVME_GETFEAT_SELECT_MASK  0x7
+#define NVME_GETFEAT_SELECT(dw10) \
+    ((dw10 >> NVME_GETFEAT_SELECT_SHIFT) & NVME_GETFEAT_SELECT_MASK)
+
+#define NVME_SETFEAT_SAVE_SHIFT 31
+#define NVME_SETFEAT_SAVE_MASK  0x1
+#define NVME_SETFEAT_SAVE(dw10) \
+    ((dw10 >> NVME_SETFEAT_SAVE_SHIFT) & NVME_SETFEAT_SAVE_MASK)
+
 typedef struct QEMU_PACKED NvmeRangeType {
     uint8_t     type;
     uint8_t     attributes;
@@ -927,6 +950,8 @@ typedef struct QEMU_PACKED NvmeLBAF {
     uint8_t     rp;
 } NvmeLBAF;
 
+#define NVME_NSID_BROADCAST 0xffffffff
+
 typedef struct QEMU_PACKED NvmeIdNs {
     uint64_t    nsze;
     uint64_t    ncap;