nvme: introduce PMR support from NVMe 1.4 spec

This patch introduces support for PMR that has been defined as part of NVMe 1.4
spec. User can now specify a pmrdev option that should point to HostMemoryBackend.
pmrdev memory region will subsequently be exposed as PCI BAR 2 in emulated NVMe
device. Guest OS can perform mmio read and writes to the PMR region that will stay
persistent across system reboot.

Signed-off-by: Andrzej Jakowski <andrzej.jakowski@linux.intel.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20200330164656.9348-1-andrzej.jakowski@linux.intel.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

4 files changed, 116 insertions, 1 deletions

diff --git a/hw/block/Makefile.objs b/hw/block/Makefile.objs
index 4b4a2b338d..47960b5f0d 100644
--- a/hw/block/Makefile.objs
+++ b/hw/block/Makefile.objs
@@ -7,12 +7,12 @@ common-obj-$(CONFIG_PFLASH_CFI02) += pflash_cfi02.o
 common-obj-$(CONFIG_XEN) += xen-block.o
 common-obj-$(CONFIG_ECC) += ecc.o
 common-obj-$(CONFIG_ONENAND) += onenand.o
-common-obj-$(CONFIG_NVME_PCI) += nvme.o
 common-obj-$(CONFIG_SWIM) += swim.o
 
 common-obj-$(CONFIG_SH4) += tc58128.o
 
 obj-$(CONFIG_VIRTIO_BLK) += virtio-blk.o
 obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk.o
+obj-$(CONFIG_NVME_PCI) += nvme.o
 
 obj-y += dataplane/
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index d28335cbf3..9b453423cf 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -19,10 +19,19 @@
  *      -drive file=<file>,if=none,id=<drive_id>
  *      -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \
  *              cmb_size_mb=<cmb_size_mb[optional]>, \
+ *              [pmrdev=<mem_backend_file_id>,] \
  *              num_queues=<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.
+ *
+ * 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.
+ * 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>, \
+ *  size=<size> .... -device nvme,...,pmrdev=<mem_id>
  */
 
 #include "qemu/osdep.h"
@@ -35,7 +44,9 @@
 #include "sysemu/sysemu.h"
 #include "qapi/error.h"
 #include "qapi/visitor.h"
+#include "sysemu/hostmem.h"
 #include "sysemu/block-backend.h"
+#include "exec/ram_addr.h"
 
 #include "qemu/log.h"
 #include "qemu/module.h"
@@ -1141,6 +1152,26 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
         NVME_GUEST_ERR(nvme_ub_mmiowr_cmbsz_readonly,
                        "invalid write to read only CMBSZ, ignored");
         return;
+    case 0xE00: /* PMRCAP */
+        NVME_GUEST_ERR(nvme_ub_mmiowr_pmrcap_readonly,
+                       "invalid write to PMRCAP register, ignored");
+        return;
+    case 0xE04: /* TODO PMRCTL */
+        break;
+    case 0xE08: /* PMRSTS */
+        NVME_GUEST_ERR(nvme_ub_mmiowr_pmrsts_readonly,
+                       "invalid write to PMRSTS register, ignored");
+        return;
+    case 0xE0C: /* PMREBS */
+        NVME_GUEST_ERR(nvme_ub_mmiowr_pmrebs_readonly,
+                       "invalid write to PMREBS register, ignored");
+        return;
+    case 0xE10: /* PMRSWTP */
+        NVME_GUEST_ERR(nvme_ub_mmiowr_pmrswtp_readonly,
+                       "invalid write to PMRSWTP register, ignored");
+        return;
+    case 0xE14: /* TODO PMRMSC */
+         break;
     default:
         NVME_GUEST_ERR(nvme_ub_mmiowr_invalid,
                        "invalid MMIO write,"
@@ -1169,6 +1200,16 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)
     }
 
     if (addr < sizeof(n->bar)) {
+        /*
+         * When PMRWBM bit 1 is set then read from
+         * from PMRSTS should ensure prior writes
+         * made it to persistent media
+         */
+        if (addr == 0xE08 &&
+            (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) {
+            qemu_ram_writeback(n->pmrdev->mr.ram_block,
+                               0, n->pmrdev->size);
+        }
         memcpy(&val, ptr + addr, size);
     } else {
         NVME_GUEST_ERR(nvme_ub_mmiord_invalid_ofs,
@@ -1332,6 +1373,23 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         error_setg(errp, "serial property not set");
         return;
     }
+
+    if (!n->cmb_size_mb && 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);
+            g_free(path);
+            return;
+        }
+
+        if (!is_power_of_2(n->pmrdev->size)) {
+            error_setg(errp, "pmr backend size needs to be power of 2 in size");
+            return;
+        }
+
+        host_memory_backend_set_mapped(n->pmrdev, true);
+    }
+
     blkconf_blocksizes(&n->conf);
     if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
                                        false, errp)) {
@@ -1415,6 +1473,51 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
             PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 |
             PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
 
+    } else if (n->pmrdev) {
+        /* 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);
+        NVME_PMRCAP_SET_WDS(n->bar.pmrcap, 0);
+        NVME_PMRCAP_SET_BIR(n->bar.pmrcap, 2);
+        NVME_PMRCAP_SET_PMRTU(n->bar.pmrcap, 0);
+        /* Turn on bit 1 support */
+        NVME_PMRCAP_SET_PMRWBM(n->bar.pmrcap, 0x02);
+        NVME_PMRCAP_SET_PMRTO(n->bar.pmrcap, 0);
+        NVME_PMRCAP_SET_CMSS(n->bar.pmrcap, 0);
+
+        /* PMR Control register */
+        n->bar.pmrctl = 0;
+        NVME_PMRCTL_SET_EN(n->bar.pmrctl, 0);
+
+        /* PMR Status register */
+        n->bar.pmrsts = 0;
+        NVME_PMRSTS_SET_ERR(n->bar.pmrsts, 0);
+        NVME_PMRSTS_SET_NRDY(n->bar.pmrsts, 0);
+        NVME_PMRSTS_SET_HSTS(n->bar.pmrsts, 0);
+        NVME_PMRSTS_SET_CBAI(n->bar.pmrsts, 0);
+
+        /* PMR Elasticity Buffer Size register */
+        n->bar.pmrebs = 0;
+        NVME_PMREBS_SET_PMRSZU(n->bar.pmrebs, 0);
+        NVME_PMREBS_SET_RBB(n->bar.pmrebs, 0);
+        NVME_PMREBS_SET_PMRWBZ(n->bar.pmrebs, 0);
+
+        /* PMR Sustained Write Throughput register */
+        n->bar.pmrswtp = 0;
+        NVME_PMRSWTP_SET_PMRSWTU(n->bar.pmrswtp, 0);
+        NVME_PMRSWTP_SET_PMRSWTV(n->bar.pmrswtp, 0);
+
+        /* PMR Memory Space Control register */
+        n->bar.pmrmsc = 0;
+        NVME_PMRMSC_SET_CMSE(n->bar.pmrmsc, 0);
+        NVME_PMRMSC_SET_CBA(n->bar.pmrmsc, 0);
+
+        pci_register_bar(pci_dev, NVME_PMRCAP_BIR(n->bar.pmrcap),
+            PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 |
+            PCI_BASE_ADDRESS_MEM_PREFETCH, &n->pmrdev->mr);
     }
 
     for (i = 0; i < n->num_namespaces; i++) {
@@ -1445,11 +1548,17 @@ static void nvme_exit(PCIDevice *pci_dev)
     if (n->cmb_size_mb) {
         g_free(n->cmbuf);
     }
+
+    if (n->pmrdev) {
+        host_memory_backend_set_mapped(n->pmrdev, false);
+    }
     msix_uninit_exclusive_bar(pci_dev);
 }
 
 static Property nvme_props[] = {
     DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf),
+    DEFINE_PROP_LINK("pmrdev", NvmeCtrl, pmrdev, TYPE_MEMORY_BACKEND,
+                     HostMemoryBackend *),
     DEFINE_PROP_STRING("serial", NvmeCtrl, serial),
     DEFINE_PROP_UINT32("cmb_size_mb", NvmeCtrl, cmb_size_mb, 0),
     DEFINE_PROP_UINT32("num_queues", NvmeCtrl, num_queues, 64),
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 557194ee19..6520a9f0be 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -83,6 +83,8 @@ typedef struct NvmeCtrl {
     uint64_t    timestamp_set_qemu_clock_ms;    /* QEMU clock time */
 
     char            *serial;
+    HostMemoryBackend *pmrdev;
+
     NvmeNamespace   *namespaces;
     NvmeSQueue      **sq;
     NvmeCQueue      **cq;
diff --git a/hw/block/trace-events b/hw/block/trace-events
index bf6d11b58b..aca54bda14 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -110,6 +110,10 @@ nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CA
 nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)"
 nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored"
 nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored"
+nvme_ub_mmiowr_pmrcap_readonly(void) "invalid write to read only PMRCAP, ignored"
+nvme_ub_mmiowr_pmrsts_readonly(void) "invalid write to read only PMRSTS, ignored"
+nvme_ub_mmiowr_pmrebs_readonly(void) "invalid write to read only PMREBS, ignored"
+nvme_ub_mmiowr_pmrswtp_readonly(void) "invalid write to read only PMRSWTP, ignored"
 nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64""
 nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64""
 nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64""