[07/17] hw/block/nvme: add support for the asynchronous event request command

From: Klaus Jensen <k.jensen@samsung.com>

Add support for the Asynchronous Event Request command. Required for
compliance with NVMe revision 1.3d. See NVM Express 1.3d, Section 5.2
("Asynchronous Event Request command").

Mostly imported from Keith's qemu-nvme tree. Modified with a max number
of queued events (controllable with the aer_max_queued device
parameter). The spec states that the controller *should* retain
events, so we do best effort here.

Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 hw/block/nvme.c       | 180 ++++++++++++++++++++++++++++++++++++++++--
 hw/block/nvme.h       |  10 ++-
 hw/block/trace-events |   9 +++
 include/block/nvme.h  |   8 +-
 4 files changed, 198 insertions(+), 9 deletions(-)

Looks good,

Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>

On Mon, 2020-06-29 at 20:26 +0200, Klaus Jensen wrote:
> From: Klaus Jensen <k.jensen@samsung.com>
> 
> Add support for the Asynchronous Event Request command. Required for
> compliance with NVMe revision 1.3d. See NVM Express 1.3d, Section 5.2
> ("Asynchronous Event Request command").
> 
> Mostly imported from Keith's qemu-nvme tree. Modified with a max number
> of queued events (controllable with the aer_max_queued device
> parameter). The spec states that the controller *should* retain
> events, so we do best effort here.
> 
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
> Acked-by: Keith Busch <kbusch@kernel.org>
> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
> ---
>  hw/block/nvme.c       | 180 ++++++++++++++++++++++++++++++++++++++++--
>  hw/block/nvme.h       |  10 ++-
>  hw/block/trace-events |   9 +++
>  include/block/nvme.h  |   8 +-
>  4 files changed, 198 insertions(+), 9 deletions(-)
> 
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index fe5d052ab159..39e680a15c56 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -342,6 +342,85 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
>      timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
>  }
>  
> +static void nvme_process_aers(void *opaque)
> +{
> +    NvmeCtrl *n = opaque;
> +    NvmeAsyncEvent *event, *next;
> +
> +    trace_pci_nvme_process_aers(n->aer_queued);
> +
> +    QTAILQ_FOREACH_SAFE(event, &n->aer_queue, entry, next) {
> +        NvmeRequest *req;
> +        NvmeAerResult *result;
> +
> +        /* can't post cqe if there is nothing to complete */
> +        if (!n->outstanding_aers) {
> +            trace_pci_nvme_no_outstanding_aers();
> +            break;
> +        }
> +
> +        /* ignore if masked (cqe posted, but event not cleared) */
> +        if (n->aer_mask & (1 << event->result.event_type)) {
> +            trace_pci_nvme_aer_masked(event->result.event_type, n->aer_mask);
> +            continue;
> +        }
> +
> +        QTAILQ_REMOVE(&n->aer_queue, event, entry);
> +        n->aer_queued--;
> +
> +        n->aer_mask |= 1 << event->result.event_type;
> +        n->outstanding_aers--;
> +
> +        req = n->aer_reqs[n->outstanding_aers];
> +
> +        result = (NvmeAerResult *) &req->cqe.result;
> +        result->event_type = event->result.event_type;
> +        result->event_info = event->result.event_info;
> +        result->log_page = event->result.log_page;
> +        g_free(event);
> +
> +        req->status = NVME_SUCCESS;
> +
> +        trace_pci_nvme_aer_post_cqe(result->event_type, result->event_info,
> +                                    result->log_page);
> +
> +        nvme_enqueue_req_completion(&n->admin_cq, req);
> +    }
> +}
> +
> +static void nvme_enqueue_event(NvmeCtrl *n, uint8_t event_type,
> +                               uint8_t event_info, uint8_t log_page)
> +{
> +    NvmeAsyncEvent *event;
> +
> +    trace_pci_nvme_enqueue_event(event_type, event_info, log_page);
> +
> +    if (n->aer_queued == n->params.aer_max_queued) {
> +        trace_pci_nvme_enqueue_event_noqueue(n->aer_queued);
> +        return;
> +    }
> +
> +    event = g_new(NvmeAsyncEvent, 1);
> +    event->result = (NvmeAerResult) {
> +        .event_type = event_type,
> +        .event_info = event_info,
> +        .log_page   = log_page,
> +    };
> +
> +    QTAILQ_INSERT_TAIL(&n->aer_queue, event, entry);
> +    n->aer_queued++;
> +
> +    nvme_process_aers(n);
> +}
> +
> +static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type)
> +{
> +    n->aer_mask &= ~(1 << event_type);
> +    if (!QTAILQ_EMPTY(&n->aer_queue)) {
> +        nvme_process_aers(n);
> +    }
> +}
> +
>  static void nvme_rw_cb(void *opaque, int ret)
>  {
>      NvmeRequest *req = opaque;
> @@ -592,8 +671,9 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
>      return NVME_SUCCESS;
>  }
>  
> -static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> -                                uint64_t off, NvmeRequest *req)
> +static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> +                                uint32_t buf_len, uint64_t off,
> +                                NvmeRequest *req)
>  {
>      uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1);
>      uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2);
> @@ -642,6 +722,10 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
>      smart.power_on_hours[0] =
>          cpu_to_le64((((current_ms - n->starttime_ms) / 1000) / 60) / 60);
>  
> +    if (!rae) {
> +        nvme_clear_events(n, NVME_AER_TYPE_SMART);
> +    }
> +
>      return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
>                               prp2);
>  }
> @@ -668,14 +752,19 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
>                               prp2);
>  }
>  
> -static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> -                                uint64_t off, NvmeRequest *req)
> +static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> +                                uint32_t buf_len, uint64_t off,
> +                                NvmeRequest *req)
>  {
>      uint32_t trans_len;
>      uint64_t prp1 = le64_to_cpu(cmd->dptr.prp1);
>      uint64_t prp2 = le64_to_cpu(cmd->dptr.prp2);
>      NvmeErrorLog errlog;
>  
> +    if (!rae) {
> +        nvme_clear_events(n, NVME_AER_TYPE_ERROR);
> +    }
> +
>      if (off > sizeof(errlog)) {
>          return NVME_INVALID_FIELD | NVME_DNR;
>      }
> @@ -716,9 +805,9 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>  
>      switch (lid) {
>      case NVME_LOG_ERROR_INFO:
> -        return nvme_error_info(n, cmd, len, off, req);
> +        return nvme_error_info(n, cmd, rae, len, off, req);
>      case NVME_LOG_SMART_INFO:
> -        return nvme_smart_info(n, cmd, len, off, req);
> +        return nvme_smart_info(n, cmd, rae, len, off, req);
>      case NVME_LOG_FW_SLOT_INFO:
>          return nvme_fw_log_info(n, cmd, len, off, req);
>      default:
> @@ -1000,6 +1089,9 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>                               ((n->params.max_ioqpairs - 1) << 16));
>          trace_pci_nvme_getfeat_numq(result);
>          break;
> +    case NVME_ASYNCHRONOUS_EVENT_CONF:
> +        result = cpu_to_le32(n->features.async_config);
> +        break;
>      case NVME_TIMESTAMP:
>          return nvme_get_feature_timestamp(n, cmd);
>      default:
> @@ -1051,6 +1143,14 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>              return NVME_INVALID_FIELD | NVME_DNR;
>          }
>  
> +        if (((n->temperature >= n->features.temp_thresh_hi) ||
> +            (n->temperature <= n->features.temp_thresh_low)) &&
> +            NVME_AEC_SMART(n->features.async_config) & NVME_SMART_TEMPERATURE) {
> +            nvme_enqueue_event(n, NVME_AER_TYPE_SMART,
> +                               NVME_AER_INFO_SMART_TEMP_THRESH,
> +                               NVME_LOG_SMART_INFO);
> +        }
> +
>          break;
>      case NVME_VOLATILE_WRITE_CACHE:
>          blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
> @@ -1063,6 +1163,9 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>          req->cqe.result = cpu_to_le32((n->params.max_ioqpairs - 1) |
>                                        ((n->params.max_ioqpairs - 1) << 16));
>          break;
> +    case NVME_ASYNCHRONOUS_EVENT_CONF:
> +        n->features.async_config = dw11;
> +        break;
>      case NVME_TIMESTAMP:
>          return nvme_set_feature_timestamp(n, cmd);
>      default:
> @@ -1072,6 +1175,25 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>      return NVME_SUCCESS;
>  }
>  
> +static uint16_t nvme_aer(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> +    trace_pci_nvme_aer(nvme_cid(req));
> +
> +    if (n->outstanding_aers > n->params.aerl) {
> +        trace_pci_nvme_aer_aerl_exceeded();
> +        return NVME_AER_LIMIT_EXCEEDED;
> +    }
> +
> +    n->aer_reqs[n->outstanding_aers] = req;
> +    n->outstanding_aers++;
> +
> +    if (!QTAILQ_EMPTY(&n->aer_queue)) {
> +        nvme_process_aers(n);
> +    }
> +
> +    return NVME_NO_COMPLETE;
> +}
> +
>  static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>  {
>      trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), cmd->opcode);
> @@ -1095,6 +1217,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>          return nvme_set_feature(n, cmd, req);
>      case NVME_ADM_CMD_GET_FEATURES:
>          return nvme_get_feature(n, cmd, req);
> +    case NVME_ADM_CMD_ASYNC_EV_REQ:
> +        return nvme_aer(n, cmd, req);
>      default:
>          trace_pci_nvme_err_invalid_admin_opc(cmd->opcode);
>          return NVME_INVALID_OPCODE | NVME_DNR;
> @@ -1149,6 +1273,15 @@ static void nvme_clear_ctrl(NvmeCtrl *n)
>          }
>      }
>  
> +    while (!QTAILQ_EMPTY(&n->aer_queue)) {
> +        NvmeAsyncEvent *event = QTAILQ_FIRST(&n->aer_queue);
> +        QTAILQ_REMOVE(&n->aer_queue, event, entry);
> +        g_free(event);
> +    }
> +
> +    n->aer_queued = 0;
> +    n->outstanding_aers = 0;
> +
>      blk_flush(n->conf.blk);
>      n->bar.cc = 0;
>  }
> @@ -1245,6 +1378,8 @@ static int nvme_start_ctrl(NvmeCtrl *n)
>  
>      nvme_set_timestamp(n, 0ULL);
>  
> +    QTAILQ_INIT(&n->aer_queue);
> +
>      return 0;
>  }
>  
> @@ -1466,6 +1601,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
>                             "completion queue doorbell write"
>                             " for nonexistent queue,"
>                             " sqid=%"PRIu32", ignoring", qid);
> +
> +            if (n->outstanding_aers) {
> +                nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> +                                   NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
> +                                   NVME_LOG_ERROR_INFO);
> +            }
> +
>              return;
>          }
>  
> @@ -1476,6 +1618,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
>                             " beyond queue size, sqid=%"PRIu32","
>                             " new_head=%"PRIu16", ignoring",
>                             qid, new_head);
> +
> +            if (n->outstanding_aers) {
> +                nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> +                                   NVME_AER_INFO_ERR_INVALID_DB_VALUE,
> +                                   NVME_LOG_ERROR_INFO);
> +            }
> +
>              return;
>          }
>  
> @@ -1506,6 +1655,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
>                             "submission queue doorbell write"
>                             " for nonexistent queue,"
>                             " sqid=%"PRIu32", ignoring", qid);
> +
> +            if (n->outstanding_aers) {
> +                nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> +                                   NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
> +                                   NVME_LOG_ERROR_INFO);
> +            }
> +
>              return;
>          }
>  
> @@ -1516,6 +1672,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
>                             " beyond queue size, sqid=%"PRIu32","
>                             " new_tail=%"PRIu16", ignoring",
>                             qid, new_tail);
> +
> +            if (n->outstanding_aers) {
> +                nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> +                                   NVME_AER_INFO_ERR_INVALID_DB_VALUE,
> +                                   NVME_LOG_ERROR_INFO);
> +            }
> +
>              return;
>          }
>  
> @@ -1637,6 +1800,7 @@ static void nvme_init_state(NvmeCtrl *n)
>      n->temperature = NVME_TEMPERATURE;
>      n->features.temp_thresh_hi = NVME_TEMPERATURE_WARNING;
>      n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
> +    n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1);
>  }
>  
>  static void nvme_init_blk(NvmeCtrl *n, Error **errp)
> @@ -1792,6 +1956,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
>       * inconsequential.
>       */
>      id->acl = 3;
> +    id->aerl = n->params.aerl;
>      id->frmw = (NVME_NUM_FW_SLOTS << 1) | NVME_FRMW_SLOT1_RO;
>      id->lpa = NVME_LPA_EXTENDED;
>  
> @@ -1866,6 +2031,7 @@ static void nvme_exit(PCIDevice *pci_dev)
>      g_free(n->namespaces);
>      g_free(n->cq);
>      g_free(n->sq);
> +    g_free(n->aer_reqs);
>  
>      if (n->params.cmb_size_mb) {
>          g_free(n->cmbuf);
> @@ -1886,6 +2052,8 @@ static Property nvme_props[] = {
>      DEFINE_PROP_UINT32("num_queues", NvmeCtrl, params.num_queues, 0),
>      DEFINE_PROP_UINT32("max_ioqpairs", NvmeCtrl, params.max_ioqpairs, 64),
>      DEFINE_PROP_UINT16("msix_qsize", NvmeCtrl, params.msix_qsize, 65),
> +    DEFINE_PROP_UINT8("aerl", NvmeCtrl, params.aerl, 3),
> +    DEFINE_PROP_UINT32("aer_max_queued", NvmeCtrl, params.aer_max_queued, 64),
>      DEFINE_PROP_END_OF_LIST(),
>  };
>  
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index 3ddbc3722d7c..1f64a0e94035 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -9,10 +9,12 @@ typedef struct NvmeParams {
>      uint32_t max_ioqpairs;
>      uint16_t msix_qsize;
>      uint32_t cmb_size_mb;
> +    uint8_t  aerl;
> +    uint32_t aer_max_queued;
>  } NvmeParams;
>  
>  typedef struct NvmeAsyncEvent {
> -    QSIMPLEQ_ENTRY(NvmeAsyncEvent) entry;
> +    QTAILQ_ENTRY(NvmeAsyncEvent) entry;
>      NvmeAerResult result;
>  } NvmeAsyncEvent;
>  
> @@ -94,6 +96,7 @@ typedef struct NvmeCtrl {
>      uint32_t    num_namespaces;
>      uint32_t    max_q_ents;
>      uint64_t    ns_size;
> +    uint8_t     outstanding_aers;
>      uint8_t     *cmbuf;
>      uint32_t    irq_status;
>      uint64_t    host_timestamp;                 /* Timestamp sent by the host */
> @@ -103,6 +106,11 @@ typedef struct NvmeCtrl {
>  
>      HostMemoryBackend *pmrdev;
>  
> +    uint8_t     aer_mask;
> +    NvmeRequest **aer_reqs;
> +    QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue;
> +    int         aer_queued;
> +
>      NvmeNamespace   *namespaces;
>      NvmeSQueue      **sq;
>      NvmeCQueue      **cq;
> diff --git a/hw/block/trace-events b/hw/block/trace-events
> index 3330d74e48db..091af16ca7d7 100644
> --- a/hw/block/trace-events
> +++ b/hw/block/trace-events
> @@ -51,6 +51,15 @@ 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"
>  pci_nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
>  pci_nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
> +pci_nvme_process_aers(int queued) "queued %d"
> +pci_nvme_aer(uint16_t cid) "cid %"PRIu16""
> +pci_nvme_aer_aerl_exceeded(void) "aerl exceeded"
> +pci_nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8""
> +pci_nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
> +pci_nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
> +pci_nvme_enqueue_event_noqueue(int queued) "queued %d"
> +pci_nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8""
> +pci_nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs"
>  pci_nvme_enqueue_req_completion(uint16_t cid, uint16_t cqid, uint16_t status) "cid %"PRIu16" cqid %"PRIu16" status 0x%"PRIx16""
>  pci_nvme_mmio_read(uint64_t addr) "addr 0x%"PRIx64""
>  pci_nvme_mmio_write(uint64_t addr, uint64_t data) "addr 0x%"PRIx64" data 0x%"PRIx64""
> diff --git a/include/block/nvme.h b/include/block/nvme.h
> index 1339f0491d27..e98584e38134 100644
> --- a/include/block/nvme.h
> +++ b/include/block/nvme.h
> @@ -597,8 +597,8 @@ enum NvmeAsyncEventRequest {
>      NVME_AER_TYPE_SMART                     = 1,
>      NVME_AER_TYPE_IO_SPECIFIC               = 6,
>      NVME_AER_TYPE_VENDOR_SPECIFIC           = 7,
> -    NVME_AER_INFO_ERR_INVALID_SQ            = 0,
> -    NVME_AER_INFO_ERR_INVALID_DB            = 1,
> +    NVME_AER_INFO_ERR_INVALID_DB_REGISTER   = 0,
> +    NVME_AER_INFO_ERR_INVALID_DB_VALUE      = 1,
>      NVME_AER_INFO_ERR_DIAG_FAIL             = 2,
>      NVME_AER_INFO_ERR_PERS_INTERNAL_ERR     = 3,
>      NVME_AER_INFO_ERR_TRANS_INTERNAL_ERR    = 4,
> @@ -902,6 +902,10 @@ typedef struct NvmeFeatureVal {
>  
>  #define NVME_TEMP_TMPTH(temp) ((temp >>  0) & 0xffff)
>  
> +#define NVME_AEC_SMART(aec)         (aec & 0xff)
> +#define NVME_AEC_NS_ATTR(aec)       ((aec >> 8) & 0x1)
> +#define NVME_AEC_FW_ACTIVATION(aec) ((aec >> 9) & 0x1)
> +
>  enum NvmeFeatureIds {
>      NVME_ARBITRATION                = 0x1,
>      NVME_POWER_MANAGEMENT           = 0x2,