diff mbox series

[v6,10/42] nvme: refactor device realization

Message ID 20200316142928.153431-11-its@irrelevant.dk (mailing list archive)
State New, archived
Headers show
Series nvme: support NVMe v1.3d, SGLs and multiple namespaces | expand

Commit Message

Klaus Jensen March 16, 2020, 2:28 p.m. UTC 
From: Klaus Jensen <k.jensen@samsung.com>

This patch splits up nvme_realize into multiple individual functions,
each initializing a different subset of the device.

Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
Acked-by: Keith Busch <kbusch@kernel.org>
---
 hw/block/nvme.c | 178 ++++++++++++++++++++++++++++++------------------
 hw/block/nvme.h |  23 ++++++-
 2 files changed, 134 insertions(+), 67 deletions(-)

Comments

Maxim Levitsky March 25, 2020, 10:40 a.m. UTC | #1 
On Mon, 2020-03-16 at 07:28 -0700, Klaus Jensen wrote:
> From: Klaus Jensen <k.jensen@samsung.com>
> 
> This patch splits up nvme_realize into multiple individual functions,
> each initializing a different subset of the device.
> 
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> Acked-by: Keith Busch <kbusch@kernel.org>
> ---
>  hw/block/nvme.c | 178 ++++++++++++++++++++++++++++++------------------
>  hw/block/nvme.h |  23 ++++++-
>  2 files changed, 134 insertions(+), 67 deletions(-)
> 
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 7dfd8a1a392d..665485045066 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -44,6 +44,8 @@
>  #include "trace.h"
>  #include "nvme.h"
>  
> +#define NVME_CMB_BIR 2
> +
>  #define NVME_GUEST_ERR(trace, fmt, ...) \
>      do { \
>          (trace_##trace)(__VA_ARGS__); \
> @@ -63,7 +65,7 @@ static inline bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
>  
>  static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
>  {
> -    if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
> +    if (n->bar.cmbsz && nvme_addr_is_cmb(n, addr)) {
>          memcpy(buf, (void *)&n->cmbuf[addr - n->ctrl_mem.addr], size);
>          return;
>      }
> @@ -157,7 +159,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
>      if (unlikely(!prp1)) {
>          trace_nvme_dev_err_invalid_prp();
>          return NVME_INVALID_FIELD | NVME_DNR;
> -    } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr &&
> +    } else if (n->bar.cmbsz && prp1 >= n->ctrl_mem.addr &&
>                 prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) {
>          qsg->nsg = 0;
>          qemu_iovec_init(iov, num_prps);
> @@ -1324,14 +1326,9 @@ static const MemoryRegionOps nvme_cmb_ops = {
>      },
>  };
>  
> -static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> +static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
>  {
> -    NvmeCtrl *n = NVME(pci_dev);
> -    NvmeIdCtrl *id = &n->id_ctrl;
> -
> -    int i;
> -    int64_t bs_size;
> -    uint8_t *pci_conf;
> +    NvmeParams *params = &n->params;
>  
>      if (n->params.num_queues) {
>          warn_report("nvme: num_queues is deprecated; please use max_ioqpairs "
> @@ -1340,57 +1337,100 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
>          n->params.max_ioqpairs = n->params.num_queues - 1;
>      }
>  
> -    if (!n->params.max_ioqpairs) {
> -        error_setg(errp, "max_ioqpairs can't be less than 1");
> +    if (params->max_ioqpairs < 1 ||
> +        params->max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
> +        error_setg(errp, "nvme: max_ioqpairs must be ");
Looks like the error message is not complete now.
> +        return -1;
>      }
>  
>      if (!n->conf.blk) {
> -        error_setg(errp, "drive property not set");
> -        return;
> +        error_setg(errp, "nvme: block backend not configured");
> +        return -1;
>      }
>  
> -    bs_size = blk_getlength(n->conf.blk);
> -    if (bs_size < 0) {
> -        error_setg(errp, "could not get backing file size");
> -        return;
> +    if (!params->serial) {
> +        error_setg(errp, "nvme: serial not configured");
> +        return -1;
>      }
>  
> -    if (!n->params.serial) {
> -        error_setg(errp, "serial property not set");
> -        return;
> -    }
> +    return 0;
> +}
> +
> +static int nvme_init_blk(NvmeCtrl *n, Error **errp)
> +{
>      blkconf_blocksizes(&n->conf);
>      if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
>                                         false, errp)) {
> -        return;
> +        return -1;
>      }
>  
> -    pci_conf = pci_dev->config;
> -    pci_conf[PCI_INTERRUPT_PIN] = 1;
> -    pci_config_set_prog_interface(pci_dev->config, 0x2);
> -    pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
> -    pcie_endpoint_cap_init(pci_dev, 0x80);
> +    return 0;
> +}
>  
> +static void nvme_init_state(NvmeCtrl *n)
> +{
>      n->num_namespaces = 1;
>      n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
> -    n->ns_size = bs_size / (uint64_t)n->num_namespaces;
> -
>      n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
>      n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
>      n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
> +}
>  
> -    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
> -                          "nvme", n->reg_size);
> -    pci_register_bar(pci_dev, 0,
> -        PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
> -        &n->iomem);
> +static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
> +{
> +    NVME_CMBLOC_SET_BIR(n->bar.cmbloc, NVME_CMB_BIR);
> +    NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
> +
> +    NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
> +    NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
> +    NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
> +    NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
> +    NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
> +    NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2);
> +    NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
> +
> +    n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
> +    memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
> +                          "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
> +    pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
> +                     PCI_BASE_ADDRESS_SPACE_MEMORY |
> +                     PCI_BASE_ADDRESS_MEM_TYPE_64 |
> +                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
> +}
> +
> +static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
> +{
> +    uint8_t *pci_conf = pci_dev->config;
> +
> +    pci_conf[PCI_INTERRUPT_PIN] = 1;
> +    pci_config_set_prog_interface(pci_conf, 0x2);
> +    pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_INTEL);
> +    pci_config_set_device_id(pci_conf, 0x5845);
> +    pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
> +    pcie_endpoint_cap_init(pci_dev, 0x80);
> +
> +    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
> +                          n->reg_size);
> +    pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
> +                     PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
>      msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
>  
> +    if (n->params.cmb_size_mb) {
> +        nvme_init_cmb(n, pci_dev);
> +    }
> +}
> +
> +static void nvme_init_ctrl(NvmeCtrl *n)
> +{
> +    NvmeIdCtrl *id = &n->id_ctrl;
> +    NvmeParams *params = &n->params;
> +    uint8_t *pci_conf = n->parent_obj.config;
> +
>      id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
>      id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
>      strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
>      strpadcpy((char *)id->fr, sizeof(id->fr), "1.0", ' ');
> -    strpadcpy((char *)id->sn, sizeof(id->sn), n->params.serial, ' ');
> +    strpadcpy((char *)id->sn, sizeof(id->sn), params->serial, ' ');
>      id->rab = 6;
>      id->ieee[0] = 0x00;
>      id->ieee[1] = 0x02;
> @@ -1431,46 +1471,54 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
>  
>      n->bar.vs = 0x00010200;
>      n->bar.intmc = n->bar.intms = 0;
> +}
>  
> -    if (n->params.cmb_size_mb) {
> +static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
> +{
> +    int64_t bs_size;
> +    NvmeIdNs *id_ns = &ns->id_ns;
>  
> -        NVME_CMBLOC_SET_BIR(n->bar.cmbloc, 2);
> -        NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
> +    bs_size = blk_getlength(n->conf.blk);
> +    if (bs_size < 0) {
> +        error_setg_errno(errp, -bs_size, "blk_getlength");
> +        return -1;
> +    }
>  
> -        NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
> -        NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
> -        NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
> -        NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
> -        NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
> -        NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */
> -        NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
> +    id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
> +    n->ns_size = bs_size;
>  
> -        n->cmbloc = n->bar.cmbloc;
> -        n->cmbsz = n->bar.cmbsz;
> +    id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns));
>  
> -        n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
> -        memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
> -                              "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
> -        pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
> -            PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 |
> -            PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
> +    /* no thin provisioning */
> +    id_ns->ncap = id_ns->nsze;
> +    id_ns->nuse = id_ns->ncap;
>  
> +    return 0;
> +}
> +
> +static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> +{
> +    NvmeCtrl *n = NVME(pci_dev);
> +    int i;
> +
> +    if (nvme_check_constraints(n, errp)) {
> +        return;
> +    }
> +
> +    nvme_init_state(n);
> +
> +    if (nvme_init_blk(n, errp)) {
> +        return;
>      }
>  
>      for (i = 0; i < n->num_namespaces; i++) {
> -        NvmeNamespace *ns = &n->namespaces[i];
> -        NvmeIdNs *id_ns = &ns->id_ns;
> -        id_ns->nsfeat = 0;
> -        id_ns->nlbaf = 0;
> -        id_ns->flbas = 0;
> -        id_ns->mc = 0;
> -        id_ns->dpc = 0;
> -        id_ns->dps = 0;
> -        id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
> -        id_ns->ncap  = id_ns->nuse = id_ns->nsze =
> -            cpu_to_le64(n->ns_size >>
> -                id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas)].ds);
> +        if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
> +            return;
> +        }
>      }
> +
> +    nvme_init_pci(n, pci_dev);
> +    nvme_init_ctrl(n);
>  }
>  
>  static void nvme_exit(PCIDevice *pci_dev)
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index 98f5b9479244..b7c465560eea 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -67,6 +67,22 @@ typedef struct NvmeNamespace {
>      NvmeIdNs        id_ns;
>  } NvmeNamespace;
>  
> +static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns)
> +{
> +    NvmeIdNs *id_ns = &ns->id_ns;
> +    return &id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)];
> +}
> +
> +static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns)
> +{
> +    return nvme_ns_lbaf(ns)->ds;
> +}
> +
> +static inline size_t nvme_ns_lbads_bytes(NvmeNamespace *ns)
> +{
> +    return 1 << nvme_ns_lbads(ns);
> +}
> +
>  #define TYPE_NVME "nvme"
>  #define NVME(obj) \
>          OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME)
> @@ -88,8 +104,6 @@ typedef struct NvmeCtrl {
>      uint32_t    num_namespaces;
>      uint32_t    max_q_ents;
>      uint64_t    ns_size;
> -    uint32_t    cmbsz;
> -    uint32_t    cmbloc;
>      uint8_t     *cmbuf;
>      uint64_t    irq_status;
>      uint64_t    host_timestamp;                 /* Timestamp sent by the host */
> @@ -103,4 +117,9 @@ typedef struct NvmeCtrl {
>      NvmeIdCtrl      id_ctrl;
>  } NvmeCtrl;
>  
> +static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +    return n->ns_size >> nvme_ns_lbads(ns);
> +}
> +
>  #endif /* HW_NVME_H */

Small nitpick: To be honest this not only refactoring in the device realization since you also (rightfully)
removed the duplicated cmbsz/cmbloc so I would add a mention for this in the commit message.
But that doesn't matter that much, so

Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>

Best regards,
	Maxim Levitsky
Klaus Jensen March 31, 2020, 5:40 a.m. UTC | #2 
On Mar 25 12:40, Maxim Levitsky wrote:
> On Mon, 2020-03-16 at 07:28 -0700, Klaus Jensen wrote:
> > From: Klaus Jensen <k.jensen@samsung.com>
> > 
> > This patch splits up nvme_realize into multiple individual functions,
> > each initializing a different subset of the device.
> > 
> > Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> > Acked-by: Keith Busch <kbusch@kernel.org>
> > ---
> >  hw/block/nvme.c | 178 ++++++++++++++++++++++++++++++------------------
> >  hw/block/nvme.h |  23 ++++++-
> >  2 files changed, 134 insertions(+), 67 deletions(-)
> > 
> > diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> > index 7dfd8a1a392d..665485045066 100644
> > --- a/hw/block/nvme.c
> > +++ b/hw/block/nvme.c
> > @@ -1340,57 +1337,100 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> >          n->params.max_ioqpairs = n->params.num_queues - 1;
> >      }
> >  
> > -    if (!n->params.max_ioqpairs) {
> > -        error_setg(errp, "max_ioqpairs can't be less than 1");
> > +    if (params->max_ioqpairs < 1 ||
> > +        params->max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
> > +        error_setg(errp, "nvme: max_ioqpairs must be ");
> Looks like the error message is not complete now.

Fixed!

> 
> Small nitpick: To be honest this not only refactoring in the device realization since you also (rightfully)
> removed the duplicated cmbsz/cmbloc so I would add a mention for this in the commit message.
> But that doesn't matter that much, so
> 

You are right. I've added it as a separate patch.

> Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
> 
> Best regards,
> 	Maxim Levitsky
>
diff mbox series

Patch

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 7dfd8a1a392d..665485045066 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -44,6 +44,8 @@ 
 #include "trace.h"
 #include "nvme.h"
 
+#define NVME_CMB_BIR 2
+
 #define NVME_GUEST_ERR(trace, fmt, ...) \
     do { \
         (trace_##trace)(__VA_ARGS__); \
@@ -63,7 +65,7 @@  static inline bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
 
 static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
 {
-    if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
+    if (n->bar.cmbsz && nvme_addr_is_cmb(n, addr)) {
         memcpy(buf, (void *)&n->cmbuf[addr - n->ctrl_mem.addr], size);
         return;
     }
@@ -157,7 +159,7 @@  static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
     if (unlikely(!prp1)) {
         trace_nvme_dev_err_invalid_prp();
         return NVME_INVALID_FIELD | NVME_DNR;
-    } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr &&
+    } else if (n->bar.cmbsz && prp1 >= n->ctrl_mem.addr &&
                prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) {
         qsg->nsg = 0;
         qemu_iovec_init(iov, num_prps);
@@ -1324,14 +1326,9 @@  static const MemoryRegionOps nvme_cmb_ops = {
     },
 };
 
-static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
 {
-    NvmeCtrl *n = NVME(pci_dev);
-    NvmeIdCtrl *id = &n->id_ctrl;
-
-    int i;
-    int64_t bs_size;
-    uint8_t *pci_conf;
+    NvmeParams *params = &n->params;
 
     if (n->params.num_queues) {
         warn_report("nvme: num_queues is deprecated; please use max_ioqpairs "
@@ -1340,57 +1337,100 @@  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         n->params.max_ioqpairs = n->params.num_queues - 1;
     }
 
-    if (!n->params.max_ioqpairs) {
-        error_setg(errp, "max_ioqpairs can't be less than 1");
+    if (params->max_ioqpairs < 1 ||
+        params->max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
+        error_setg(errp, "nvme: max_ioqpairs must be ");
+        return -1;
     }
 
     if (!n->conf.blk) {
-        error_setg(errp, "drive property not set");
-        return;
+        error_setg(errp, "nvme: block backend not configured");
+        return -1;
     }
 
-    bs_size = blk_getlength(n->conf.blk);
-    if (bs_size < 0) {
-        error_setg(errp, "could not get backing file size");
-        return;
+    if (!params->serial) {
+        error_setg(errp, "nvme: serial not configured");
+        return -1;
     }
 
-    if (!n->params.serial) {
-        error_setg(errp, "serial property not set");
-        return;
-    }
+    return 0;
+}
+
+static int nvme_init_blk(NvmeCtrl *n, Error **errp)
+{
     blkconf_blocksizes(&n->conf);
     if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
                                        false, errp)) {
-        return;
+        return -1;
     }
 
-    pci_conf = pci_dev->config;
-    pci_conf[PCI_INTERRUPT_PIN] = 1;
-    pci_config_set_prog_interface(pci_dev->config, 0x2);
-    pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
-    pcie_endpoint_cap_init(pci_dev, 0x80);
+    return 0;
+}
 
+static void nvme_init_state(NvmeCtrl *n)
+{
     n->num_namespaces = 1;
     n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
-    n->ns_size = bs_size / (uint64_t)n->num_namespaces;
-
     n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
     n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
     n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
+}
 
-    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
-                          "nvme", n->reg_size);
-    pci_register_bar(pci_dev, 0,
-        PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
-        &n->iomem);
+static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
+{
+    NVME_CMBLOC_SET_BIR(n->bar.cmbloc, NVME_CMB_BIR);
+    NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
+
+    NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
+    NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
+    NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2);
+    NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
+
+    n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+    memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
+                          "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+    pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
+                     PCI_BASE_ADDRESS_SPACE_MEMORY |
+                     PCI_BASE_ADDRESS_MEM_TYPE_64 |
+                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
+}
+
+static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
+{
+    uint8_t *pci_conf = pci_dev->config;
+
+    pci_conf[PCI_INTERRUPT_PIN] = 1;
+    pci_config_set_prog_interface(pci_conf, 0x2);
+    pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_INTEL);
+    pci_config_set_device_id(pci_conf, 0x5845);
+    pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
+    pcie_endpoint_cap_init(pci_dev, 0x80);
+
+    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
+                          n->reg_size);
+    pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
+                     PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
     msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
 
+    if (n->params.cmb_size_mb) {
+        nvme_init_cmb(n, pci_dev);
+    }
+}
+
+static void nvme_init_ctrl(NvmeCtrl *n)
+{
+    NvmeIdCtrl *id = &n->id_ctrl;
+    NvmeParams *params = &n->params;
+    uint8_t *pci_conf = n->parent_obj.config;
+
     id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
     id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
     strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
     strpadcpy((char *)id->fr, sizeof(id->fr), "1.0", ' ');
-    strpadcpy((char *)id->sn, sizeof(id->sn), n->params.serial, ' ');
+    strpadcpy((char *)id->sn, sizeof(id->sn), params->serial, ' ');
     id->rab = 6;
     id->ieee[0] = 0x00;
     id->ieee[1] = 0x02;
@@ -1431,46 +1471,54 @@  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 
     n->bar.vs = 0x00010200;
     n->bar.intmc = n->bar.intms = 0;
+}
 
-    if (n->params.cmb_size_mb) {
+static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
+{
+    int64_t bs_size;
+    NvmeIdNs *id_ns = &ns->id_ns;
 
-        NVME_CMBLOC_SET_BIR(n->bar.cmbloc, 2);
-        NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
+    bs_size = blk_getlength(n->conf.blk);
+    if (bs_size < 0) {
+        error_setg_errno(errp, -bs_size, "blk_getlength");
+        return -1;
+    }
 
-        NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
-        NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
-        NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */
-        NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
+    id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
+    n->ns_size = bs_size;
 
-        n->cmbloc = n->bar.cmbloc;
-        n->cmbsz = n->bar.cmbsz;
+    id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns));
 
-        n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
-        memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
-                              "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
-        pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
-            PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 |
-            PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
+    /* no thin provisioning */
+    id_ns->ncap = id_ns->nsze;
+    id_ns->nuse = id_ns->ncap;
 
+    return 0;
+}
+
+static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+{
+    NvmeCtrl *n = NVME(pci_dev);
+    int i;
+
+    if (nvme_check_constraints(n, errp)) {
+        return;
+    }
+
+    nvme_init_state(n);
+
+    if (nvme_init_blk(n, errp)) {
+        return;
     }
 
     for (i = 0; i < n->num_namespaces; i++) {
-        NvmeNamespace *ns = &n->namespaces[i];
-        NvmeIdNs *id_ns = &ns->id_ns;
-        id_ns->nsfeat = 0;
-        id_ns->nlbaf = 0;
-        id_ns->flbas = 0;
-        id_ns->mc = 0;
-        id_ns->dpc = 0;
-        id_ns->dps = 0;
-        id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
-        id_ns->ncap  = id_ns->nuse = id_ns->nsze =
-            cpu_to_le64(n->ns_size >>
-                id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas)].ds);
+        if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
+            return;
+        }
     }
+
+    nvme_init_pci(n, pci_dev);
+    nvme_init_ctrl(n);
 }
 
 static void nvme_exit(PCIDevice *pci_dev)
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 98f5b9479244..b7c465560eea 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -67,6 +67,22 @@  typedef struct NvmeNamespace {
     NvmeIdNs        id_ns;
 } NvmeNamespace;
 
+static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns)
+{
+    NvmeIdNs *id_ns = &ns->id_ns;
+    return &id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)];
+}
+
+static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns)
+{
+    return nvme_ns_lbaf(ns)->ds;
+}
+
+static inline size_t nvme_ns_lbads_bytes(NvmeNamespace *ns)
+{
+    return 1 << nvme_ns_lbads(ns);
+}
+
 #define TYPE_NVME "nvme"
 #define NVME(obj) \
         OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME)
@@ -88,8 +104,6 @@  typedef struct NvmeCtrl {
     uint32_t    num_namespaces;
     uint32_t    max_q_ents;
     uint64_t    ns_size;
-    uint32_t    cmbsz;
-    uint32_t    cmbloc;
     uint8_t     *cmbuf;
     uint64_t    irq_status;
     uint64_t    host_timestamp;                 /* Timestamp sent by the host */
@@ -103,4 +117,9 @@  typedef struct NvmeCtrl {
     NvmeIdCtrl      id_ctrl;
 } NvmeCtrl;
 
+static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
+{
+    return n->ns_size >> nvme_ns_lbads(ns);
+}
+
 #endif /* HW_NVME_H */