hw/nvme: Add support for SR-IOV

This patch implements initial support for Single Root I/O Virtualization
on an NVMe device.

Essentially, it allows to define the maximum number of virtual functions
supported by the NVMe controller via sriov_max_vfs parameter.

Passing a non-zero value to sriov_max_vfs triggers reporting of SR-IOV
capability by a physical controller and ARI capability by both the
physical and virtual function devices.

NVMe controllers created via virtual functions mirror functionally
the physical controller, which may not entirely be the case, thus
consideration would be needed on the way to limit the capabilities of
the VF.

NVMe subsystem is required for the use of SR-IOV.

Signed-off-by: Lukasz Maniak <lukasz.maniak@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>

1 files changed, 82 insertions, 3 deletions

diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index 1e6e0fcad9..855ab55aa4 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -35,6 +35,7 @@
  *              mdts=<N[optional]>,vsl=<N[optional]>, \
  *              zoned.zasl=<N[optional]>, \
  *              zoned.auto_transition=<on|off[optional]>, \
+ *              sriov_max_vfs=<N[optional]> \
  *              subsys=<subsys_id>
  *      -device nvme-ns,drive=<drive_id>,bus=<bus_name>,nsid=<nsid>,\
  *              zoned=<true|false[optional]>, \
@@ -106,6 +107,12 @@
  *   transitioned to zone state closed for resource management purposes.
  *   Defaults to 'on'.
  *
+ * - `sriov_max_vfs`
+ *   Indicates the maximum number of PCIe virtual functions supported
+ *   by the controller. The default value is 0. Specifying a non-zero value
+ *   enables reporting of both SR-IOV and ARI capabilities by the NVMe device.
+ *   Virtual function controllers will not report SR-IOV capability.
+ *
  * nvme namespace device parameters
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  * - `shared`
@@ -160,6 +167,7 @@
 #include "sysemu/block-backend.h"
 #include "sysemu/hostmem.h"
 #include "hw/pci/msix.h"
+#include "hw/pci/pcie_sriov.h"
 #include "migration/vmstate.h"
 
 #include "nvme.h"
@@ -176,6 +184,9 @@
 #define NVME_TEMPERATURE_CRITICAL 0x175
 #define NVME_NUM_FW_SLOTS 1
 #define NVME_DEFAULT_MAX_ZA_SIZE (128 * KiB)
+#define NVME_MAX_VFS 127
+#define NVME_VF_OFFSET 0x1
+#define NVME_VF_STRIDE 1
 
 #define NVME_GUEST_ERR(trace, fmt, ...) \
     do { \
@@ -5888,6 +5899,10 @@ static void nvme_ctrl_reset(NvmeCtrl *n)
         g_free(event);
     }
 
+    if (!pci_is_vf(&n->parent_obj) && n->params.sriov_max_vfs) {
+        pcie_sriov_pf_disable_vfs(&n->parent_obj);
+    }
+
     n->aer_queued = 0;
     n->outstanding_aers = 0;
     n->qs_created = false;
@@ -6569,6 +6584,29 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp)
         error_setg(errp, "vsl must be non-zero");
         return;
     }
+
+    if (params->sriov_max_vfs) {
+        if (!n->subsys) {
+            error_setg(errp, "subsystem is required for the use of SR-IOV");
+            return;
+        }
+
+        if (params->sriov_max_vfs > NVME_MAX_VFS) {
+            error_setg(errp, "sriov_max_vfs must be between 0 and %d",
+                       NVME_MAX_VFS);
+            return;
+        }
+
+        if (params->cmb_size_mb) {
+            error_setg(errp, "CMB is not supported with SR-IOV");
+            return;
+        }
+
+        if (n->pmr.dev) {
+            error_setg(errp, "PMR is not supported with SR-IOV");
+            return;
+        }
+    }
 }
 
 static void nvme_init_state(NvmeCtrl *n)
@@ -6626,6 +6664,20 @@ static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev)
     memory_region_set_enabled(&n->pmr.dev->mr, false);
 }
 
+static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset,
+                            uint64_t bar_size)
+{
+    uint16_t vf_dev_id = n->params.use_intel_id ?
+                         PCI_DEVICE_ID_INTEL_NVME : PCI_DEVICE_ID_REDHAT_NVME;
+
+    pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id,
+                       n->params.sriov_max_vfs, n->params.sriov_max_vfs,
+                       NVME_VF_OFFSET, NVME_VF_STRIDE);
+
+    pcie_sriov_pf_init_vf_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
+                              PCI_BASE_ADDRESS_MEM_TYPE_64, bar_size);
+}
+
 static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
 {
     uint8_t *pci_conf = pci_dev->config;
@@ -6640,7 +6692,7 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
 
     if (n->params.use_intel_id) {
         pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_INTEL);
-        pci_config_set_device_id(pci_conf, 0x5845);
+        pci_config_set_device_id(pci_conf, PCI_DEVICE_ID_INTEL_NVME);
     } else {
         pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_REDHAT);
         pci_config_set_device_id(pci_conf, PCI_DEVICE_ID_REDHAT_NVME);
@@ -6648,6 +6700,9 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
 
     pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
     pcie_endpoint_cap_init(pci_dev, 0x80);
+    if (n->params.sriov_max_vfs) {
+        pcie_ari_init(pci_dev, 0x100, 1);
+    }
 
     bar_size = QEMU_ALIGN_UP(n->reg_size, 4 * KiB);
     msix_table_offset = bar_size;
@@ -6666,8 +6721,12 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
                           n->reg_size);
     memory_region_add_subregion(&n->bar0, 0, &n->iomem);
 
-    pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
-                     PCI_BASE_ADDRESS_MEM_TYPE_64, &n->bar0);
+    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, &err);
@@ -6688,6 +6747,10 @@ static int nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         nvme_init_pmr(n, pci_dev);
     }
 
+    if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs) {
+        nvme_init_sriov(n, pci_dev, 0x120, bar_size);
+    }
+
     return 0;
 }
 
@@ -6838,6 +6901,16 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     NvmeCtrl *n = NVME(pci_dev);
     NvmeNamespace *ns;
     Error *local_err = NULL;
+    NvmeCtrl *pn = NVME(pcie_sriov_get_pf(pci_dev));
+
+    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.
+         */
+        memcpy(&n->params, &pn->params, sizeof(NvmeParams));
+        n->subsys = pn->subsys;
+    }
 
     nvme_check_constraints(n, &local_err);
     if (local_err) {
@@ -6902,6 +6975,11 @@ static void nvme_exit(PCIDevice *pci_dev)
     if (n->pmr.dev) {
         host_memory_backend_set_mapped(n->pmr.dev, false);
     }
+
+    if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs) {
+        pcie_sriov_pf_exit(pci_dev);
+    }
+
     msix_uninit(pci_dev, &n->bar0, &n->bar0);
     memory_region_del_subregion(&n->bar0, &n->iomem);
 }
@@ -6926,6 +7004,7 @@ static Property nvme_props[] = {
     DEFINE_PROP_UINT8("zoned.zasl", NvmeCtrl, params.zasl, 0),
     DEFINE_PROP_BOOL("zoned.auto_transition", NvmeCtrl,
                      params.auto_transition_zones, true),
+    DEFINE_PROP_UINT8("sriov_max_vfs", NvmeCtrl, params.sriov_max_vfs, 0),
     DEFINE_PROP_END_OF_LIST(),
 };