[PATCH v4 2/2] nvme: allow cmb and pmr to be enabled on same device

[Andrzej Jakowski <andrzej.jakowski@linux.intel.com>]

So far it was not possible to have CMB and PMR emulated on the same
device, because BAR2 was used exclusively either of PMR or CMB. This
patch places CMB at BAR4 offset so it not conflicts with MSI-X vectors.

Signed-off-by: Andrzej Jakowski <andrzej.jakowski@linux.intel.com>
---
 hw/block/nvme.c      | 101 +++++++++++++++++++++++++++++--------------
 hw/block/nvme.h      |   1 +
 include/block/nvme.h |   4 +-
 3 files changed, 72 insertions(+), 34 deletions(-)

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 9f11f3e9da..f5156bcfe5 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -22,12 +22,12 @@
  *              [pmrdev=<mem_backend_file_id>,] \
  *              max_ioqpairs=<N[optional]>
  *
- * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at
- * offset 0 in BAR2 and supports only WDS, RDS and SQS for now.
+ * Note cmb_size_mb denotes size of CMB in MB. CMB when configured is assumed
+ * to be resident in BAR4 at certain offset - this is because BAR4 is also
+ * used for storing MSI-X table that is available at offset 0 in BAR4.
  *
- * cmb_size_mb= and pmrdev= options are mutually exclusive due to limitation
- * in available BAR's. cmb_size_mb= will take precedence over pmrdev= when
- * both provided.
+ * pmrdev is assumed to be resident in BAR2/BAR3. When configured it consumes
+ * whole BAR2/BAR3 exclusively.
  * Enabling pmr emulation can be achieved by pointing to memory-backend-file.
  * For example:
  * -object memory-backend-file,id=<mem_id>,share=on,mem-path=<file_path>, \
@@ -57,8 +57,8 @@
 #define NVME_MAX_IOQPAIRS 0xffff
 #define NVME_REG_SIZE 0x1000
 #define NVME_DB_SIZE  4
-#define NVME_CMB_BIR 2
 #define NVME_PMR_BIR 2
+#define NVME_MSIX_BIR 4
 
 #define NVME_GUEST_ERR(trace, fmt, ...) \
     do { \
@@ -1395,7 +1395,7 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp)
         return;
     }
 
-    if (!n->params.cmb_size_mb && n->pmrdev) {
+    if (n->pmrdev) {
         if (host_memory_backend_is_mapped(n->pmrdev)) {
             char *path = object_get_canonical_path_component(OBJECT(n->pmrdev));
             error_setg(errp, "can't use already busy memdev: %s", path);
@@ -1453,33 +1453,70 @@ static void nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
     id_ns->nuse = id_ns->ncap;
 }
 
-static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
+static void nvme_bar4_init(PCIDevice *pci_dev, Error **errp)
 {
-    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); /* MBs */
-    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),
+    NvmeCtrl *n = NVME(pci_dev);
+    int status;
+    uint64_t bar_size, cmb_offset = 0;
+    uint32_t msix_vectors;
+    uint32_t nvme_pba_offset;
+    uint32_t cmb_size_units;
+
+    msix_vectors = n->params.max_ioqpairs + 1;
+    nvme_pba_offset = PCI_MSIX_ENTRY_SIZE * msix_vectors;
+    bar_size = nvme_pba_offset + QEMU_ALIGN_UP(msix_vectors, 64) / 8;
+
+    if (n->params.cmb_size_mb) {
+        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);
+
+        cmb_size_units = NVME_CMBSZ_GETSIZEUNITS(n->bar.cmbsz);
+        cmb_offset = QEMU_ALIGN_UP(bar_size, cmb_size_units);
+
+        NVME_CMBLOC_SET_BIR(n->bar.cmbloc, NVME_MSIX_BIR);
+        NVME_CMBLOC_SET_OFST(n->bar.cmbloc, cmb_offset / cmb_size_units);
+
+        n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+
+        bar_size += cmb_offset;
+        bar_size += NVME_CMBSZ_GETSIZE(n->bar.cmbsz);
+    }
+
+    bar_size = pow2ceil(bar_size);
+
+    /* Create memory region for BAR4, then overlap cmb, msix and pba
+     * tables on top of it.*/
+    memory_region_init(&n->bar4, OBJECT(n), "nvme-bar4", bar_size);
+
+    if (n->params.cmb_size_mb) {
+        memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
+                              "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+
+        memory_region_add_subregion(&n->bar4, cmb_offset, &n->ctrl_mem);
+    }
+
+    status = msix_init(pci_dev, n->params.msix_qsize,
+                       &n->bar4, NVME_MSIX_BIR, 0,
+                       &n->bar4, NVME_MSIX_BIR, nvme_pba_offset,
+                       0, errp);
+
+    if (status) {
+        return;
+    }
+
+    pci_register_bar(pci_dev, NVME_MSIX_BIR,
                      PCI_BASE_ADDRESS_SPACE_MEMORY |
                      PCI_BASE_ADDRESS_MEM_TYPE_64 |
-                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
+                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->bar4);
 }
 
 static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev)
 {
-    /* Controller Capabilities register */
-    NVME_CAP_SET_PMRS(n->bar.cap, 1);
-
     /* PMR Capabities register */
     n->bar.pmrcap = 0;
     NVME_PMRCAP_SET_RDS(n->bar.pmrcap, 0);
@@ -1537,13 +1574,10 @@ static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
                           n->reg_size);
     pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
                      PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
-    if (msix_init_exclusive_bar(pci_dev, n->params.msix_qsize, 4, errp)) {
-        return;
-    }
 
-    if (n->params.cmb_size_mb) {
-        nvme_init_cmb(n, pci_dev);
-    } else if (n->pmrdev) {
+    nvme_bar4_init(pci_dev, errp);
+
+    if (n->pmrdev) {
         nvme_init_pmr(n, pci_dev);
     }
 }
@@ -1583,6 +1617,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
     NVME_CAP_SET_CSS(n->bar.cap, 1);
     NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
     NVME_CAP_SET_CMBS(n->bar.cap, n->params.cmb_size_mb ? 1 : 0);
+    NVME_CAP_SET_PMRS(n->bar.cap, n->pmrdev ? 1 : 0);
 
     n->bar.vs = 0x00010200;
     n->bar.intmc = n->bar.intms = 0;
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 1d30c0bca2..b2b9d727a5 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -81,6 +81,7 @@ typedef struct NvmeCtrl {
     PCIDevice    parent_obj;
     MemoryRegion iomem;
     MemoryRegion ctrl_mem;
+    MemoryRegion bar4;
     NvmeBar      bar;
     BlockConf    conf;
     NvmeParams   params;
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 14cf398dfa..76d15bdf9f 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -216,9 +216,11 @@ enum NvmeCmbszMask {
     (cmbsz |= (uint64_t)(val & CMBSZ_SZU_MASK) << CMBSZ_SZU_SHIFT)
 #define NVME_CMBSZ_SET_SZ(cmbsz, val)    \
     (cmbsz |= (uint64_t)(val & CMBSZ_SZ_MASK) << CMBSZ_SZ_SHIFT)
+#define NVME_CMBSZ_GETSIZEUNITS(cmbsz) \
+    (1 << (12 + 4 * NVME_CMBSZ_SZU(cmbsz)))
 
 #define NVME_CMBSZ_GETSIZE(cmbsz) \
-    (NVME_CMBSZ_SZ(cmbsz) * (1 << (12 + 4 * NVME_CMBSZ_SZU(cmbsz))))
+    (NVME_CMBSZ_SZ(cmbsz) * NVME_CMBSZ_GETSIZEUNITS(cmbsz))
 
 enum NvmePmrcapShift {
     PMRCAP_RDS_SHIFT      = 3,
-- 
2.21.1