summary refs log tree commit diff stats
path: root/hw/nvme/ctrl.c
diff options
context:
space:
mode:
Diffstat (limited to 'hw/nvme/ctrl.c')
-rw-r--r--hw/nvme/ctrl.c97
1 files changed, 70 insertions, 27 deletions
diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index 40159f39b8..c2b17de987 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -2855,7 +2855,7 @@ static inline uint16_t nvme_check_copy_mcl(NvmeNamespace *ns,
         uint32_t nlb;
         nvme_copy_source_range_parse(iocb->ranges, idx, iocb->format, NULL,
                                      &nlb, NULL, NULL, NULL);
-        copy_len += nlb + 1;
+        copy_len += nlb;
     }
 
     if (copy_len > ns->id_ns.mcl) {
@@ -5642,6 +5642,10 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req)
     } QEMU_PACKED uuid = {};
     struct {
         NvmeIdNsDescr hdr;
+        uint8_t v[NVME_NIDL_NGUID];
+    } QEMU_PACKED nguid = {};
+    struct {
+        NvmeIdNsDescr hdr;
         uint64_t v;
     } QEMU_PACKED eui64 = {};
     struct {
@@ -5668,6 +5672,14 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req)
         pos += sizeof(uuid);
     }
 
+    if (!nvme_nguid_is_null(&ns->params.nguid)) {
+        nguid.hdr.nidt = NVME_NIDT_NGUID;
+        nguid.hdr.nidl = NVME_NIDL_NGUID;
+        memcpy(nguid.v, ns->params.nguid.data, NVME_NIDL_NGUID);
+        memcpy(pos, &nguid, sizeof(nguid));
+        pos += sizeof(nguid);
+    }
+
     if (ns->params.eui64) {
         eui64.hdr.nidt = NVME_NIDT_EUI64;
         eui64.hdr.nidl = NVME_NIDL_EUI64;
@@ -7794,6 +7806,11 @@ static bool nvme_check_params(NvmeCtrl *n, Error **errp)
     }
 
     if (n->pmr.dev) {
+        if (params->msix_exclusive_bar) {
+            error_setg(errp, "not enough BARs available to enable PMR");
+            return false;
+        }
+
         if (host_memory_backend_is_mapped(n->pmr.dev)) {
             error_setg(errp, "can't use already busy memdev: %s",
                        object_get_canonical_path_component(OBJECT(n->pmr.dev)));
@@ -7999,13 +8016,18 @@ static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev)
     memory_region_set_enabled(&n->pmr.dev->mr, false);
 }
 
-static uint64_t nvme_bar_size(unsigned total_queues, unsigned total_irqs,
-                              unsigned *msix_table_offset,
-                              unsigned *msix_pba_offset)
+static uint64_t nvme_mbar_size(unsigned total_queues, unsigned total_irqs,
+                               unsigned *msix_table_offset,
+                               unsigned *msix_pba_offset)
 {
-    uint64_t bar_size, msix_table_size, msix_pba_size;
+    uint64_t bar_size, msix_table_size;
 
     bar_size = sizeof(NvmeBar) + 2 * total_queues * NVME_DB_SIZE;
+
+    if (total_irqs == 0) {
+        goto out;
+    }
+
     bar_size = QEMU_ALIGN_UP(bar_size, 4 * KiB);
 
     if (msix_table_offset) {
@@ -8020,11 +8042,10 @@ static uint64_t nvme_bar_size(unsigned total_queues, unsigned total_irqs,
         *msix_pba_offset = bar_size;
     }
 
-    msix_pba_size = QEMU_ALIGN_UP(total_irqs, 64) / 8;
-    bar_size += msix_pba_size;
+    bar_size += QEMU_ALIGN_UP(total_irqs, 64) / 8;
 
-    bar_size = pow2ceil(bar_size);
-    return bar_size;
+out:
+    return pow2ceil(bar_size);
 }
 
 static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset)
@@ -8032,7 +8053,7 @@ static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset)
     uint16_t vf_dev_id = n->params.use_intel_id ?
                          PCI_DEVICE_ID_INTEL_NVME : PCI_DEVICE_ID_REDHAT_NVME;
     NvmePriCtrlCap *cap = &n->pri_ctrl_cap;
-    uint64_t bar_size = nvme_bar_size(le16_to_cpu(cap->vqfrsm),
+    uint64_t bar_size = nvme_mbar_size(le16_to_cpu(cap->vqfrsm),
                                       le16_to_cpu(cap->vifrsm),
                                       NULL, NULL);
 
@@ -8071,7 +8092,7 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
     ERRP_GUARD();
     uint8_t *pci_conf = pci_dev->config;
     uint64_t bar_size;
-    unsigned msix_table_offset, msix_pba_offset;
+    unsigned msix_table_offset = 0, msix_pba_offset = 0;
     int ret;
 
     pci_conf[PCI_INTERRUPT_PIN] = 1;
@@ -8093,24 +8114,38 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         pcie_ari_init(pci_dev, 0x100);
     }
 
-    /* add one to max_ioqpairs to account for the admin queue pair */
-    bar_size = nvme_bar_size(n->params.max_ioqpairs + 1, n->params.msix_qsize,
-                             &msix_table_offset, &msix_pba_offset);
+    if (n->params.msix_exclusive_bar && !pci_is_vf(pci_dev)) {
+        bar_size = nvme_mbar_size(n->params.max_ioqpairs + 1, 0, NULL, NULL);
+        memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
+                              bar_size);
+        pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
+                         PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
+        ret = msix_init_exclusive_bar(pci_dev, n->params.msix_qsize, 4, errp);
+    } else {
+        assert(n->params.msix_qsize >= 1);
 
-    memory_region_init(&n->bar0, OBJECT(n), "nvme-bar0", bar_size);
-    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
-                          msix_table_offset);
-    memory_region_add_subregion(&n->bar0, 0, &n->iomem);
+        /* add one to max_ioqpairs to account for the admin queue pair */
+        bar_size = nvme_mbar_size(n->params.max_ioqpairs + 1,
+                                  n->params.msix_qsize, &msix_table_offset,
+                                  &msix_pba_offset);
 
-    if (pci_is_vf(pci_dev)) {
-        pcie_sriov_vf_register_bar(pci_dev, 0, &n->bar0);
-    } else {
-        pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
-                         PCI_BASE_ADDRESS_MEM_TYPE_64, &n->bar0);
+        memory_region_init(&n->bar0, OBJECT(n), "nvme-bar0", bar_size);
+        memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
+                              msix_table_offset);
+        memory_region_add_subregion(&n->bar0, 0, &n->iomem);
+
+        if (pci_is_vf(pci_dev)) {
+            pcie_sriov_vf_register_bar(pci_dev, 0, &n->bar0);
+        } else {
+            pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
+                             PCI_BASE_ADDRESS_MEM_TYPE_64, &n->bar0);
+        }
+
+        ret = msix_init(pci_dev, n->params.msix_qsize,
+                        &n->bar0, 0, msix_table_offset,
+                        &n->bar0, 0, msix_pba_offset, 0, errp);
     }
-    ret = msix_init(pci_dev, n->params.msix_qsize,
-                    &n->bar0, 0, msix_table_offset,
-                    &n->bar0, 0, msix_pba_offset, 0, errp);
+
     if (ret == -ENOTSUP) {
         /* report that msix is not supported, but do not error out */
         warn_report_err(*errp);
@@ -8305,9 +8340,15 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     if (pci_is_vf(pci_dev)) {
         /*
          * VFs derive settings from the parent. PF's lifespan exceeds
-         * that of VF's, so it's safe to share params.serial.
+         * that of VF's.
          */
         memcpy(&n->params, &pn->params, sizeof(NvmeParams));
+
+        /*
+         * Set PF's serial value to a new string memory to prevent 'serial'
+         * property object release of PF when a VF is removed from the system.
+         */
+        n->params.serial = g_strdup(pn->params.serial);
         n->subsys = pn->subsys;
     }
 
@@ -8408,6 +8449,8 @@ static Property nvme_props[] = {
                       params.sriov_max_vi_per_vf, 0),
     DEFINE_PROP_UINT8("sriov_max_vq_per_vf", NvmeCtrl,
                       params.sriov_max_vq_per_vf, 0),
+    DEFINE_PROP_BOOL("msix-exclusive-bar", NvmeCtrl, params.msix_exclusive_bar,
+                     false),
     DEFINE_PROP_END_OF_LIST(),
 };