hw/block/nvme: Add Commands Supported and Effects log

This log page becomes necessary to implement to allow checking for
Zone Append command support in Zoned Namespace Command Set.

This commit adds the code to report this log page for NVM Command
Set only. The parts that are specific to zoned operation will be
added later in the series.

All incoming admin and i/o commands are now only processed if their
corresponding support bits are set in this log. This provides an
easy way to control what commands to support and what not to
depending on set CC.CSS.

Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Niklas Cassel <Niklas.Cassel@wdc.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>

4 files changed, 114 insertions, 9 deletions

diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
index aeca810fc7..bdeaf1c0de 100644
--- a/hw/block/nvme-ns.h
+++ b/hw/block/nvme-ns.h
@@ -30,6 +30,7 @@ typedef struct NvmeNamespace {
     int32_t      bootindex;
     int64_t      size;
     NvmeIdNs     id_ns;
+    const uint32_t *iocs;
 
     NvmeNamespaceParams params;
 
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 4d1ca8c466..05e799623c 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -112,6 +112,30 @@ static const uint32_t nvme_feature_cap[NVME_FID_MAX] = {
     [NVME_TIMESTAMP]                = NVME_FEAT_CAP_CHANGE,
 };
 
+static const uint32_t nvme_cse_acs[256] = {
+    [NVME_ADM_CMD_DELETE_SQ]        = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_CREATE_SQ]        = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_GET_LOG_PAGE]     = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_DELETE_CQ]        = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_CREATE_CQ]        = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_IDENTIFY]         = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_ABORT]            = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_SET_FEATURES]     = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_GET_FEATURES]     = NVME_CMD_EFF_CSUPP,
+    [NVME_ADM_CMD_ASYNC_EV_REQ]     = NVME_CMD_EFF_CSUPP,
+};
+
+static const uint32_t nvme_cse_iocs_none[256];
+
+static const uint32_t nvme_cse_iocs_nvm[256] = {
+    [NVME_CMD_FLUSH]                = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_LBCC,
+    [NVME_CMD_WRITE_ZEROES]         = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_LBCC,
+    [NVME_CMD_WRITE]                = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_LBCC,
+    [NVME_CMD_READ]                 = NVME_CMD_EFF_CSUPP,
+    [NVME_CMD_DSM]                  = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_LBCC,
+    [NVME_CMD_COMPARE]              = NVME_CMD_EFF_CSUPP,
+};
+
 static void nvme_process_sq(void *opaque);
 
 static uint16_t nvme_cid(NvmeRequest *req)
@@ -1306,10 +1330,6 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req)
     trace_pci_nvme_io_cmd(nvme_cid(req), nsid, nvme_sqid(req),
                           req->cmd.opcode, nvme_io_opc_str(req->cmd.opcode));
 
-    if (NVME_CC_CSS(n->bar.cc) == NVME_CC_CSS_ADMIN_ONLY) {
-        return NVME_INVALID_OPCODE | NVME_DNR;
-    }
-
     if (!nvme_nsid_valid(n, nsid)) {
         return NVME_INVALID_NSID | NVME_DNR;
     }
@@ -1319,6 +1339,11 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req)
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
+    if (!(req->ns->iocs[req->cmd.opcode] & NVME_CMD_EFF_CSUPP)) {
+        trace_pci_nvme_err_invalid_opc(req->cmd.opcode);
+        return NVME_INVALID_OPCODE | NVME_DNR;
+    }
+
     switch (req->cmd.opcode) {
     case NVME_CMD_FLUSH:
         return nvme_flush(n, req);
@@ -1333,9 +1358,10 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req)
     case NVME_CMD_DSM:
         return nvme_dsm(n, req);
     default:
-        trace_pci_nvme_err_invalid_opc(req->cmd.opcode);
-        return NVME_INVALID_OPCODE | NVME_DNR;
+        assert(false);
     }
+
+    return NVME_INVALID_OPCODE | NVME_DNR;
 }
 
 static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n)
@@ -1570,6 +1596,37 @@ static uint16_t nvme_error_info(NvmeCtrl *n, uint8_t rae, uint32_t buf_len,
                     DMA_DIRECTION_FROM_DEVICE, req);
 }
 
+static uint16_t nvme_cmd_effects(NvmeCtrl *n, uint32_t buf_len,
+                                 uint64_t off, NvmeRequest *req)
+{
+    NvmeEffectsLog log = {};
+    const uint32_t *src_iocs = NULL;
+    uint32_t trans_len;
+
+    if (off >= sizeof(log)) {
+        trace_pci_nvme_err_invalid_log_page_offset(off, sizeof(log));
+        return NVME_INVALID_FIELD | NVME_DNR;
+    }
+
+    switch (NVME_CC_CSS(n->bar.cc)) {
+    case NVME_CC_CSS_NVM:
+        src_iocs = nvme_cse_iocs_nvm;
+    case NVME_CC_CSS_ADMIN_ONLY:
+        break;
+    }
+
+    memcpy(log.acs, nvme_cse_acs, sizeof(nvme_cse_acs));
+
+    if (src_iocs) {
+        memcpy(log.iocs, src_iocs, sizeof(log.iocs));
+    }
+
+    trans_len = MIN(sizeof(log) - off, buf_len);
+
+    return nvme_dma(n, ((uint8_t *)&log) + off, trans_len,
+                    DMA_DIRECTION_FROM_DEVICE, req);
+}
+
 static uint16_t nvme_get_log(NvmeCtrl *n, NvmeRequest *req)
 {
     NvmeCmd *cmd = &req->cmd;
@@ -1613,6 +1670,8 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeRequest *req)
         return nvme_smart_info(n, rae, len, off, req);
     case NVME_LOG_FW_SLOT_INFO:
         return nvme_fw_log_info(n, len, off, req);
+    case NVME_LOG_CMD_EFFECTS:
+        return nvme_cmd_effects(n, len, off, req);
     default:
         trace_pci_nvme_err_invalid_log_page(nvme_cid(req), lid);
         return NVME_INVALID_FIELD | NVME_DNR;
@@ -2229,6 +2288,11 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req)
     trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), req->cmd.opcode,
                              nvme_adm_opc_str(req->cmd.opcode));
 
+    if (!(nvme_cse_acs[req->cmd.opcode] & NVME_CMD_EFF_CSUPP)) {
+        trace_pci_nvme_err_invalid_admin_opc(req->cmd.opcode);
+        return NVME_INVALID_OPCODE | NVME_DNR;
+    }
+
     switch (req->cmd.opcode) {
     case NVME_ADM_CMD_DELETE_SQ:
         return nvme_del_sq(n, req);
@@ -2251,9 +2315,10 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req)
     case NVME_ADM_CMD_ASYNC_EV_REQ:
         return nvme_aer(n, req);
     default:
-        trace_pci_nvme_err_invalid_admin_opc(req->cmd.opcode);
-        return NVME_INVALID_OPCODE | NVME_DNR;
+        assert(false);
     }
+
+    return NVME_INVALID_OPCODE | NVME_DNR;
 }
 
 static void nvme_process_sq(void *opaque)
@@ -2352,6 +2417,23 @@ static void nvme_ctrl_shutdown(NvmeCtrl *n)
     }
 }
 
+static void nvme_select_ns_iocs(NvmeCtrl *n)
+{
+    NvmeNamespace *ns;
+    int i;
+
+    for (i = 1; i <= n->num_namespaces; i++) {
+        ns = nvme_ns(n, i);
+        if (!ns) {
+            continue;
+        }
+        ns->iocs = nvme_cse_iocs_none;
+        if (NVME_CC_CSS(n->bar.cc) != NVME_CC_CSS_ADMIN_ONLY) {
+            ns->iocs = nvme_cse_iocs_nvm;
+        }
+    }
+}
+
 static int nvme_start_ctrl(NvmeCtrl *n)
 {
     uint32_t page_bits = NVME_CC_MPS(n->bar.cc) + 12;
@@ -2450,6 +2532,8 @@ static int nvme_start_ctrl(NvmeCtrl *n)
 
     QTAILQ_INIT(&n->aer_queue);
 
+    nvme_select_ns_iocs(n);
+
     return 0;
 }
 
@@ -3057,7 +3141,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
     id->acl = 3;
     id->aerl = n->params.aerl;
     id->frmw = (NVME_NUM_FW_SLOTS << 1) | NVME_FRMW_SLOT1_RO;
-    id->lpa = NVME_LPA_NS_SMART | NVME_LPA_EXTENDED;
+    id->lpa = NVME_LPA_NS_SMART | NVME_LPA_CSE | NVME_LPA_EXTENDED;
 
     /* recommended default value (~70 C) */
     id->wctemp = cpu_to_le16(NVME_TEMPERATURE_WARNING);
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 60262b03c9..9e1a17e627 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -108,6 +108,7 @@ pci_nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PR
 pci_nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8""
 pci_nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8""
 pci_nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64""
+pci_nvme_err_invalid_log_page_offset(uint64_t ofs, uint64_t size) "must be <= %"PRIu64", got %"PRIu64""
 pci_nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, sid=%"PRIu16""
 pci_nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission queue, invalid cqid=%"PRIu16""
 pci_nvme_err_invalid_create_sq_sqid(uint16_t sqid) "failed creating submission queue, invalid sqid=%"PRIu16""
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 11ac1c2b7d..397f7ca3b5 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -752,10 +752,27 @@ enum NvmeSmartWarn {
     NVME_SMART_FAILED_VOLATILE_MEDIA  = 1 << 4,
 };
 
+typedef struct NvmeEffectsLog {
+    uint32_t    acs[256];
+    uint32_t    iocs[256];
+    uint8_t     resv[2048];
+} NvmeEffectsLog;
+
+enum {
+    NVME_CMD_EFF_CSUPP      = 1 << 0,
+    NVME_CMD_EFF_LBCC       = 1 << 1,
+    NVME_CMD_EFF_NCC        = 1 << 2,
+    NVME_CMD_EFF_NIC        = 1 << 3,
+    NVME_CMD_EFF_CCC        = 1 << 4,
+    NVME_CMD_EFF_CSE_MASK   = 3 << 16,
+    NVME_CMD_EFF_UUID_SEL   = 1 << 19,
+};
+
 enum NvmeLogIdentifier {
     NVME_LOG_ERROR_INFO     = 0x01,
     NVME_LOG_SMART_INFO     = 0x02,
     NVME_LOG_FW_SLOT_INFO   = 0x03,
+    NVME_LOG_CMD_EFFECTS    = 0x05,
 };
 
 typedef struct QEMU_PACKED NvmePSD {
@@ -868,6 +885,7 @@ enum NvmeIdCtrlFrmw {
 
 enum NvmeIdCtrlLpa {
     NVME_LPA_NS_SMART = 1 << 0,
+    NVME_LPA_CSE      = 1 << 1,
     NVME_LPA_EXTENDED = 1 << 2,
 };
 
@@ -1076,6 +1094,7 @@ static inline void _nvme_check_size(void)
     QEMU_BUILD_BUG_ON(sizeof(NvmeErrorLog) != 64);
     QEMU_BUILD_BUG_ON(sizeof(NvmeFwSlotInfoLog) != 512);
     QEMU_BUILD_BUG_ON(sizeof(NvmeSmartLog) != 512);
+    QEMU_BUILD_BUG_ON(sizeof(NvmeEffectsLog) != 4096);
     QEMU_BUILD_BUG_ON(sizeof(NvmeIdCtrl) != 4096);
     QEMU_BUILD_BUG_ON(sizeof(NvmeIdNs) != 4096);
     QEMU_BUILD_BUG_ON(sizeof(NvmeSglDescriptor) != 16);