hw/nvme: add machine compatibility parameter to enable msix exclusive bar

Commit 1901b4967c3f ("hw/block/nvme: move msix table and pba to BAR 0")
moved the MSI-X table and PBA to BAR 0 to make room for enabling CMR and
PMR at the same time. As reported by Julien Grall in #2184, this breaks
migration through system hibernation.

Add a machine compatibility parameter and set it on machines pre 6.0 to
enable the old behavior automatically, restoring the hibernation
migration support.

Cc: qemu-stable@nongnu.org
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2184
Fixes: 1901b4967c3f ("hw/block/nvme: move msix table and pba to BAR 0")
Reported-by: Julien Grall julien@xen.org
Tested-by: Julien Grall julien@xen.org
Reviewed-by: Jesper Wendel Devantier <foss@defmacro.it>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>

2 files changed, 37 insertions, 15 deletions

diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index efcfd71710..036b15403a 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -7810,6 +7810,11 @@ 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)));
@@ -8113,24 +8118,38 @@ 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_mbar_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);
@@ -8434,6 +8453,8 @@ 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(),
 };
 
diff --git a/hw/nvme/nvme.h b/hw/nvme/nvme.h
index 392c029426..bed8191bd5 100644
--- a/hw/nvme/nvme.h
+++ b/hw/nvme/nvme.h
@@ -536,6 +536,7 @@ typedef struct NvmeParams {
     uint16_t sriov_vi_flexible;
     uint8_t  sriov_max_vq_per_vf;
     uint8_t  sriov_max_vi_per_vf;
+    bool     msix_exclusive_bar;
 } NvmeParams;
 
 typedef struct NvmeCtrl {