Skip to contentSkip to conversation

hw/nvme: add basic live migration support

PATCH Superseded Alexander Mikhalitsyn 1 participant 5 messages Mar 4

v2 of 10 Superseded Latest is v10 →

lore
Share & tools
lore
#0 lore raw

v2 cover hw/nvme: add basic live migration support

From: Alexander Mikhalitsyn <[email protected]>

Dear friends,

This patchset adds basic live migration support for QEMU emulated NVMe device.

Implementation has some limitations:
- only one NVMe namespace is supported
- SMART counters are not preserved
- CMB is not supported
- PMR is not supported
- SPDM is not supported
- SR-IOV is not supported

I believe this is something I can support in next patchset versions or separately on-demand (when usecase appears).

Testing.

This patch series was manually tested on:
- Debian 13.3 VM (kernel 6.12.69+deb13-amd64) using fio on *non-root* NVMe disk (root disk was virtio-scsi):

time fio --name=nvme-verify \
    --filename=/dev/nvme0n1 \
    --size=5G \
    --rw=randwrite \
    --bs=4k \
    --iodepth=16 \
    --numjobs=1 \
    --direct=0 \
    --ioengine=io_uring \
    --verify=crc32c \
    --verify_fatal=1

- Windows Server 2022 VM (NVMe drive was a *root* disk) with opened browser playing video.

No defects were found.

Changelog for version 2:
- full support for AERs (in-flight requests and queued events too)

Kind regards,
Alex

Alexander Mikhalitsyn (4):
hw/nvme: add migration blockers for non-supported cases hw/nvme: split nvme_init_sq/nvme_init_cq into helpers
migration: add VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT{8, 32}_ALLOC hw/nvme: add basic live migration support

 hw/nvme/ctrl.c              | 665 ++++++++++++++++++++++++++++++++++--
 hw/nvme/nvme.h              |   5 +
 hw/nvme/trace-events        |  11 +
 include/migration/vmstate.h |  33 ++
 migration/vmstate-types.c   |  88 +++++
 5 files changed, 772 insertions(+), 30 deletions(-)
Signature · 1 line
2.47.3
#1 lore raw

PATCH v2 1/4 hw/nvme: add migration blockers for non-supported cases

From: Alexander Mikhalitsyn <[email protected]>

Let's block migration for cases we don't support:
- SR-IOV
- CMB
- PMR
- SPDM

No functional changes here, because NVMe migration is not supported at all as of this commit.

---
 hw/nvme/ctrl.c | 35 +++++++++++++++++++++++++++++++++++
 hw/nvme/nvme.h |  3 +++
 2 files changed, 38 insertions(+)
hw/nvme/ctrl.c +35 -0
index cc4593cd427..4694bdb4d02 100644
@@ -207,6 +207,7 @@
 #include "hw/pci/msix.h"
 #include "hw/pci/pcie_sriov.h"
 #include "system/spdm-socket.h"
+#include "migration/blocker.h"
 #include "migration/vmstate.h"
 
 #include "nvme.h"
@@ -8962,6 +8963,14 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
     pcie_endpoint_cap_init(pci_dev, 0x80);
     pcie_cap_flr_init(pci_dev);
     if (n->params.sriov_max_vfs) {
+        if (n->migration_blocker == NULL) {
+            error_setg(&n->migration_blocker,
+                       "Migration is disabled when SR-IOV capability is set");
+            if (migrate_add_blocker(&n->migration_blocker, errp) < 0) {
+                return false;
+            }
+        }
+
         pcie_ari_init(pci_dev, 0x100);
     }
 
@@ -9025,6 +9034,14 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
     if (pci_dev->spdm_port) {
         uint16_t doe_offset = PCI_CONFIG_SPACE_SIZE;
 
+        if (n->migration_blocker == NULL) {
+            error_setg(&n->migration_blocker,
+                       "Migration is disabled when SPDM responder is used");
+            if (migrate_add_blocker(&n->migration_blocker, errp) < 0) {
+                return false;
+            }
+        }
+
         switch  (pci_dev->spdm_trans) {
         case SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE:
             if (n->params.sriov_max_vfs) {
@@ -9053,10 +9070,26 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
     }
 
     if (n->params.cmb_size_mb) {
+        if (n->migration_blocker == NULL) {
+            error_setg(&n->migration_blocker,
+                       "Migration is disabled when CMB feature is used");
+            if (migrate_add_blocker(&n->migration_blocker, errp) < 0) {
+                return false;
+            }
+        }
+
         nvme_init_cmb(n, pci_dev);
     }
 
     if (n->pmr.dev) {
+        if (n->migration_blocker == NULL) {
+            error_setg(&n->migration_blocker,
+                       "Migration is disabled when PMR feature is used");
+            if (migrate_add_blocker(&n->migration_blocker, errp) < 0) {
+                return false;
+            }
+        }
+
         if (!nvme_init_pmr(n, pci_dev, errp)) {
             return false;
         }
@@ -9365,6 +9398,8 @@ static void nvme_exit(PCIDevice *pci_dev)
     }
 
     memory_region_del_subregion(&n->bar0, &n->iomem);
+
+    migrate_del_blocker(&n->migration_blocker);
 }
 
 static const Property nvme_props[] = {
hw/nvme/nvme.h +3 -0
index d66f7dc82d5..457b6637249 100644
@@ -666,6 +666,9 @@ typedef struct NvmeCtrl {
 
     /* Socket mapping to SPDM over NVMe Security In/Out commands */
     int spdm_socket;
+
+    /* Migration-related stuff */
+    Error *migration_blocker;
 } NvmeCtrl;
 
 typedef enum NvmeResetType {
Signature · 1 line
2.47.3
#2 lore raw

PATCH v2 2/4 hw/nvme: split nvme_init_sq/nvme_init_cq into helpers

In reply to Alexander Mikhalitsyn

From: Alexander Mikhalitsyn <[email protected]>

---
 hw/nvme/ctrl.c | 57 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 36 insertions(+), 21 deletions(-)
hw/nvme/ctrl.c +36 -21
index 4694bdb4d02..89cc26d745b 100644
@@ -4852,18 +4852,14 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req)
     return NVME_SUCCESS;
 }
 
-static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
-                         uint16_t sqid, uint16_t cqid, uint16_t size)
+static void __nvme_init_sq(NvmeSQueue *sq)
 {
+    NvmeCtrl *n = sq->ctrl;
+    uint16_t sqid = sq->sqid;
+    uint16_t cqid = sq->cqid;
     int i;
     NvmeCQueue *cq;
 
-    sq->ctrl = n;
-    sq->dma_addr = dma_addr;
-    sq->sqid = sqid;
-    sq->size = size;
-    sq->cqid = cqid;
-    sq->head = sq->tail = 0;
     sq->io_req = g_new0(NvmeRequest, sq->size);
 
     QTAILQ_INIT(&sq->req_list);
@@ -4893,6 +4889,18 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
     n->sq[sqid] = sq;
 }
 
+static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
+                         uint16_t sqid, uint16_t cqid, uint16_t size)
+{
+    sq->ctrl = n;
+    sq->dma_addr = dma_addr;
+    sq->sqid = sqid;
+    sq->size = size;
+    sq->cqid = cqid;
+    sq->head = sq->tail = 0;
+    __nvme_init_sq(sq);
+}
+
 static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req)
 {
     NvmeSQueue *sq;
@@ -5553,24 +5561,16 @@ static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeRequest *req)
     return NVME_SUCCESS;
 }
 
-static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr,
-                         uint16_t cqid, uint16_t vector, uint16_t size,
-                         uint16_t irq_enabled)
+static void __nvme_init_cq(NvmeCQueue *cq)
 {
+    NvmeCtrl *n = cq->ctrl;
     PCIDevice *pci = PCI_DEVICE(n);
+    uint16_t cqid = cq->cqid;
 
-    if (msix_enabled(pci) && irq_enabled) {
-        msix_vector_use(pci, vector);
+    if (msix_enabled(pci) && cq->irq_enabled) {
+        msix_vector_use(pci, cq->vector);
     }
 
-    cq->ctrl = n;
-    cq->cqid = cqid;
-    cq->size = size;
-    cq->dma_addr = dma_addr;
-    cq->phase = 1;
-    cq->irq_enabled = irq_enabled;
-    cq->vector = vector;
-    cq->head = cq->tail = 0;
     QTAILQ_INIT(&cq->req_list);
     QTAILQ_INIT(&cq->sq_list);
     if (n->dbbuf_enabled) {
@@ -5588,6 +5588,21 @@ static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr,
                                  &DEVICE(cq->ctrl)->mem_reentrancy_guard);
 }
 
+static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr,
+                         uint16_t cqid, uint16_t vector, uint16_t size,
+                         uint16_t irq_enabled)
+{
+    cq->ctrl = n;
+    cq->cqid = cqid;
+    cq->size = size;
+    cq->dma_addr = dma_addr;
+    cq->phase = 1;
+    cq->irq_enabled = irq_enabled;
+    cq->vector = vector;
+    cq->head = cq->tail = 0;
+    __nvme_init_cq(cq);
+}
+
 static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req)
 {
     NvmeCQueue *cq;
Signature · 1 line
2.47.3
#3 lore raw

PATCH v2 3/4 migration: add VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT{8, 32}_ALLOC

In reply to Alexander Mikhalitsyn

From: Alexander Mikhalitsyn <[email protected]>

Add VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT{8, 32}_ALLOC, which helps to save/restore a dynamic array of pointers to structures.

v2:
- added VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT8_ALLOC

---
 include/migration/vmstate.h | 33 ++++++++++++++
 migration/vmstate-types.c   | 88 +++++++++++++++++++++++++++++++++++++
 2 files changed, 121 insertions(+)
include/migration/vmstate.h +33 -0
index 89f9f49d20a..0bbe3317740 100644
@@ -265,6 +265,7 @@ extern const VMStateInfo vmstate_info_bitmap;
 extern const VMStateInfo vmstate_info_qtailq;
 extern const VMStateInfo vmstate_info_gtree;
 extern const VMStateInfo vmstate_info_qlist;
+extern const VMStateInfo vmstate_info_ptrs_array_entry;
 
 #define type_check_2darray(t1,t2,n,m) ((t1(*)[n][m])0 - (t2*)0)
 /*
@@ -537,6 +538,38 @@ extern const VMStateInfo vmstate_info_qlist;
     .offset     = vmstate_offset_array(_s, _f, _type*, _n),          \
 }
 
+/*
+ * For migrating a dynamically allocated uint32-indexed array
+ * of pointers to structures (with NULL entries and with auto memory allocation).
+ *
+ * _type: type of structure pointed to
+ * _vmsd: VMSD for structure
+ * start: size of structure pointed to (for auto memory allocation)
+ */
+#define VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT8_ALLOC(_field, _state, _field_num, _version, _vmsd, _type) { \
+    .name       = (stringify(_field)),                                \
+    .version_id = (_version),                                         \
+    .num_offset = vmstate_offset_value(_state, _field_num, uint8_t), \
+    .info       = &vmstate_info_ptrs_array_entry,                     \
+    .vmsd       = &(_vmsd),                                           \
+    .start      = sizeof(_type),                                      \
+    .size       = sizeof(_type *),                                    \
+    .flags      = VMS_VARRAY_UINT8|VMS_POINTER,                      \
+    .offset     = vmstate_offset_pointer(_state, _field, _type *),    \
+}
+
+#define VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT32_ALLOC(_field, _state, _field_num, _version, _vmsd, _type) { \
+    .name       = (stringify(_field)),                                \
+    .version_id = (_version),                                         \
+    .num_offset = vmstate_offset_value(_state, _field_num, uint32_t), \
+    .info       = &vmstate_info_ptrs_array_entry,                     \
+    .vmsd       = &(_vmsd),                                           \
+    .start      = sizeof(_type),                                      \
+    .size       = sizeof(_type *),                                    \
+    .flags      = VMS_VARRAY_UINT32|VMS_POINTER,                      \
+    .offset     = vmstate_offset_pointer(_state, _field, _type *),    \
+}
+
 #define VMSTATE_VARRAY_OF_POINTER_UINT32(_field, _state, _field_num, _version, _info, _type) { \
     .name       = (stringify(_field)),                                    \
     .version_id = (_version),                                             \
migration/vmstate-types.c +88 -0

91 lines not on this page · raw message

Signature · 1 line
2.47.3
#4 lore raw

PATCH v2 4/4 hw/nvme: add basic live migration support

In reply to Alexander Mikhalitsyn

From: Alexander Mikhalitsyn <[email protected]>

It has some limitations:
- only one NVMe namespace is supported
- SMART counters are not preserved
- CMB is not supported
- PMR is not supported
- SPDM is not supported
- SR-IOV is not supported

v2:
- AERs are now fully supported

---
 hw/nvme/ctrl.c       | 573 ++++++++++++++++++++++++++++++++++++++++++-
 hw/nvme/nvme.h       |   2 +
 hw/nvme/trace-events |  11 +
 3 files changed, 577 insertions(+), 9 deletions(-)
hw/nvme/ctrl.c +564 -9
index 89cc26d745b..cdfda1d3be8 100644
@@ -208,6 +208,7 @@
 #include "hw/pci/pcie_sriov.h"
 #include "system/spdm-socket.h"
 #include "migration/blocker.h"
+#include "migration/qemu-file-types.h"
 #include "migration/vmstate.h"
 
 #include "nvme.h"
@@ -4901,6 +4902,25 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
     __nvme_init_sq(sq);
 }
 
+static void nvme_restore_sq(NvmeSQueue *sq_from)
+{
+    NvmeCtrl *n = sq_from->ctrl;
+    NvmeSQueue *sq = sq_from;
+
+    if (sq_from->sqid == 0) {
+        sq = &n->admin_sq;
+        sq->ctrl = n;
+        sq->dma_addr = sq_from->dma_addr;
+        sq->sqid = sq_from->sqid;
+        sq->size = sq_from->size;
+        sq->cqid = sq_from->cqid;
+        sq->head = sq_from->head;
+        sq->tail = sq_from->tail;
+    }
+
+    __nvme_init_sq(sq);
+}
+
 static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req)
 {
     NvmeSQueue *sq;
@@ -5603,6 +5623,27 @@ static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr,
     __nvme_init_cq(cq);
 }
 
+static void nvme_restore_cq(NvmeCQueue *cq_from)
+{
+    NvmeCtrl *n = cq_from->ctrl;
+    NvmeCQueue *cq = cq_from;
+
+    if (cq_from->cqid == 0) {
+        cq = &n->admin_cq;
+        cq->ctrl = n;
+        cq->cqid = cq_from->cqid;
+        cq->size = cq_from->size;
+        cq->dma_addr = cq_from->dma_addr;
+        cq->phase = cq_from->phase;
+        cq->irq_enabled = cq_from->irq_enabled;
+        cq->vector = cq_from->vector;
+        cq->head = cq_from->head;
+        cq->tail = cq_from->tail;
+    }
+
+    __nvme_init_cq(cq);
+}
+
 static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req)
 {
     NvmeCQueue *cq;
@@ -7291,7 +7332,7 @@ static uint16_t nvme_dbbuf_config(NvmeCtrl *n, const NvmeRequest *req)
     n->dbbuf_eis = eis_addr;
     n->dbbuf_enabled = true;
 
-    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
+    for (i = 0; i < n->num_queues; i++) {
         NvmeSQueue *sq = n->sq[i];
         NvmeCQueue *cq = n->cq[i];
 
@@ -7731,7 +7772,7 @@ static int nvme_atomic_write_check(NvmeCtrl *n, NvmeCmd *cmd,
     /*
      * Walk the queues to see if there are any atomic conflicts.
      */
-    for (i = 1; i < n->params.max_ioqpairs + 1; i++) {
+    for (i = 1; i < n->num_queues; i++) {
         NvmeSQueue *sq;
         NvmeRequest *req;
         NvmeRwCmd *req_rw;
@@ -7801,6 +7842,10 @@ static void nvme_process_sq(void *opaque)
     NvmeCmd cmd;
     NvmeRequest *req;
 
+    if (qatomic_read(&n->stop_processing_sq)) {
+        return;
+    }
+
     if (n->dbbuf_enabled) {
         nvme_update_sq_tail(sq);
     }
@@ -7809,6 +7854,10 @@ static void nvme_process_sq(void *opaque)
         NvmeAtomic *atomic;
         bool cmd_is_atomic;
 
+        if (qatomic_read(&n->stop_processing_sq)) {
+            return;
+        }
+
         addr = sq->dma_addr + (sq->head << NVME_SQES);
         if (nvme_addr_read(n, addr, (void *)&cmd, sizeof(cmd))) {
             trace_pci_nvme_err_addr_read(addr);
@@ -7917,12 +7966,12 @@ static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst)
         nvme_ns_drain(ns);
     }
 
-    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
+    for (i = 0; i < n->num_queues; i++) {
         if (n->sq[i] != NULL) {
             nvme_free_sq(n->sq[i], n);
         }
     }
-    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
+    for (i = 0; i < n->num_queues; i++) {
         if (n->cq[i] != NULL) {
             nvme_free_cq(n->cq[i], n);
         }
@@ -8592,6 +8641,8 @@ static bool nvme_check_params(NvmeCtrl *n, Error **errp)
         params->max_ioqpairs = params->num_queues - 1;
     }
 
+    n->num_queues = params->max_ioqpairs + 1;
+
     if (n->namespace.blkconf.blk && n->subsys) {
         error_setg(errp, "subsystem support is unavailable with legacy "
                    "namespace ('drive' property)");
@@ -8746,8 +8797,8 @@ static void nvme_init_state(NvmeCtrl *n)
         n->conf_msix_qsize = n->params.msix_qsize;
     }
 
-    n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
-    n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
+    n->sq = g_new0(NvmeSQueue *, n->num_queues);
+    n->cq = g_new0(NvmeCQueue *, n->num_queues);
     n->temperature = NVME_TEMPERATURE;
     n->features.temp_thresh_hi = NVME_TEMPERATURE_WARNING;
     n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
@@ -8990,7 +9041,7 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
     }
 
     if (n->params.msix_exclusive_bar && !pci_is_vf(pci_dev)) {
-        bar_size = nvme_mbar_size(n->params.max_ioqpairs + 1, 0, NULL, NULL);
+        bar_size = nvme_mbar_size(n->num_queues, 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 |
@@ -9002,7 +9053,7 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         /* add one to max_ioqpairs to account for the admin queue pair */
         if (!pci_is_vf(pci_dev)) {
             nr_vectors = n->params.msix_qsize;
-            bar_size = nvme_mbar_size(n->params.max_ioqpairs + 1,
+            bar_size = nvme_mbar_size(n->num_queues,
                                       nr_vectors, &msix_table_offset,
                                       &msix_pba_offset);
         } else {
@@ -9552,9 +9603,513 @@ static uint32_t nvme_pci_read_config(PCIDevice *dev, uint32_t address, int len)
     return pci_default_read_config(dev, address, len);
 }
 
+static bool nvme_ctrl_pre_save(void *opaque, Error **errp)
+{
+    NvmeCtrl *n = opaque;
+    int i;
+
+    trace_pci_nvme_pre_save_enter(n);
+
+    /* ask SQ processing code not to take new requests */
+    qatomic_set(&n->stop_processing_sq, true);
+
+    /* prevent new in-flight IO from appearing */
+    for (i = 0; i < n->num_queues; i++) {
+        NvmeSQueue *sq = n->sq[i];
+
+        if (!sq)
+            continue;
+
+        qemu_bh_cancel(sq->bh);
+    }
+
+    /* drain all IO */
+    for (i = 1; i <= NVME_MAX_NAMESPACES; i++) {
+        NvmeNamespace *ns;
+
+        ns = nvme_ns(n, i);
+        if (!ns) {
+            continue;
+        }
+
+        trace_pci_nvme_pre_save_ns_drain(n, i);
+        nvme_ns_drain(ns);
+    }
+
+    /*
+     * Now, we should take care of AERs.
+     *
+     * 1. Save all queued events (n->aer_queue).
+     *    This is done automatically, see nvme_vmstate VMStateDescription.
+     *    Here we only need to print them for debugging purpose.
+     * 2. Go over outstanding AER requests (n->aer_reqs) and check they are
+     *    all have expected opcode (NVME_ADM_CMD_ASYNC_EV_REQ) and other fields.
+     *
+     * We must be really careful here, because in case of further QEMU NVMe changes,
+     * we may break migration without noticing it, or worse, introduce silent
+     * data corruption during migration.
+     */
+    if (n->aer_queued) {
+        NvmeAsyncEvent *event;
+
+        QTAILQ_FOREACH(event, &n->aer_queue, entry) {
+            trace_pci_nvme_pre_save_aer(event->result.event_type, event->result.event_info,
+                                        event->result.log_page);
+        }
+    }
+
+    for (i = 0; i < n->outstanding_aers; i++) {
+        NvmeRequest *re = n->aer_reqs[i];
+
+        /*
+         * Can't use assert() here, because we don't want
+         * to just crash QEMU when user requests a migration.
+         */
+        if (!(re->cmd.opcode == NVME_ADM_CMD_ASYNC_EV_REQ)) {
+            error_setg(errp, "re->cmd.opcode (%u) != NVME_ADM_CMD_ASYNC_EV_REQ", re->cmd.opcode);
+            goto err;
+        }
+
+        if (!(re->ns == NULL)) {
+            error_setg(errp, "re->ns != NULL");
+            goto err;
+        }
+
+        if (!(re->sq == &n->admin_sq)) {
+            error_setg(errp, "re->sq != &n->admin_sq");
+            goto err;
+        }
+
+        if (!(re->aiocb == NULL)) {
+            error_setg(errp, "re->aiocb != NULL");
+            goto err;
+        }
+
+        if (!(re->opaque == NULL)) {
+            error_setg(errp, "re->opaque != NULL");
+            goto err;
+        }
+
+        if (!(re->atomic_write == false)) {
+            error_setg(errp, "re->atomic_write != false");
+            goto err;
+        }
+
+        if (re->sg.flags & NVME_SG_ALLOC) {
+            error_setg(errp, "unexpected NVME_SG_ALLOC flag in re->sg.flags");
+            goto err;
+        }
+    }
+
+    /* wait when all in-flight IO requests (except NVME_ADM_CMD_ASYNC_EV_REQ) are processed */
+    for (i = 0; i < n->num_queues; i++) {
+        NvmeRequest *req;
+        NvmeSQueue *sq = n->sq[i];
+
+        if (!sq)
+            continue;
+
+        trace_pci_nvme_pre_save_sq_out_req_drain_wait(n, i, sq->head, sq->tail, sq->size);
+
+wait_out_reqs:
+        QTAILQ_FOREACH(req, &sq->out_req_list, entry) {
+            if (req->cmd.opcode != NVME_ADM_CMD_ASYNC_EV_REQ) {
+                cpu_relax();
+                goto wait_out_reqs;
+            }
+        }
+
+        trace_pci_nvme_pre_save_sq_out_req_drain_wait_end(n, i, sq->head, sq->tail);
+    }
+
+    /* wait when all IO requests completions are written to guest memory */
+    for (i = 0; i < n->num_queues; i++) {
+        NvmeCQueue *cq = n->cq[i];
+
+        if (!cq)
+            continue;
+
+        trace_pci_nvme_pre_save_cq_req_drain_wait(n, i, cq->head, cq->tail, cq->size);
+
+        while (!QTAILQ_EMPTY(&cq->req_list)) {
+            /*
+             * nvme_post_cqes() can't do its job of cleaning cq->req_list
+             * when CQ is full, it means that we need to save what we have in
+             * cq->req_list and restore it back on VM resume.
+             *
+             * Good thing is that this can only happen when guest hasn't
+             * processed CQ for a long time and at the same time, many SQEs
+             * are in flight.
+             *
+             * For now, let's just block migration in this rare case.
+             */
+            if (nvme_cq_full(cq)) {
+                error_setg(errp, "no free space in CQ (not supported)");
+                goto err;
+            }
+
+            cpu_relax();
+        }
+
+        trace_pci_nvme_pre_save_cq_req_drain_wait_end(n, i, cq->head, cq->tail);
+    }
+
+    for (uint32_t nsid = 0; nsid <= NVME_MAX_NAMESPACES; nsid++) {
+        NvmeNamespace *ns = n->namespaces[nsid];
+
+        if (!ns)
+            continue;
+
+        if (ns != &n->namespace) {
+            error_setg(errp, "only one NVMe namespace is supported for migration");
+            goto err;
+        }
+    }
+
+    return true;
+
+err:
+    /* restore sq processing back to normal */
+    qatomic_set(&n->stop_processing_sq, false);
+    return false;
+}
+
+static bool nvme_ctrl_post_load(void *opaque, int version_id, Error **errp)
+{
+    NvmeCtrl *n = opaque;
+    int i;
+
+    trace_pci_nvme_post_load_enter(n);
+
+    /* restore CQs first */
+    for (i = 0; i < n->num_queues; i++) {
+        NvmeCQueue *cq = n->cq[i];
+
+        if (!cq)
+            continue;
+
+        cq->ctrl = n;
+        nvme_restore_cq(cq);
+        trace_pci_nvme_post_load_restore_cq(n, i, cq->head, cq->tail, cq->size);
+
+        if (i == 0) {
+            /*
+             * Admin CQ lives in n->admin_cq, we don't need
+             * memory allocated for it in get_ptrs_array_entry() anymore.
+             *
+             * nvme_restore_cq() also takes care of:
+             * n->cq[0] = &n->admin_cq;
+             * so n->cq[0] remains valid.
+             */
+            g_free(cq);
+        }
+    }
+
+    for (i = 0; i < n->num_queues; i++) {
+        NvmeSQueue *sq = n->sq[i];
+
+        if (!sq)
+            continue;
+
+        sq->ctrl = n;
+        nvme_restore_sq(sq);
+        trace_pci_nvme_post_load_restore_sq(n, i, sq->head, sq->tail, sq->size);
+
+        if (i == 0) {
+            /* same as for CQ */
+            g_free(sq);
+        }
+    }
+
+    if (n->aer_queued) {
+        NvmeAsyncEvent *event;
+
+        QTAILQ_FOREACH(event, &n->aer_queue, entry) {
+            trace_pci_nvme_post_load_aer(event->result.event_type, event->result.event_info,
+                                         event->result.log_page);
+        }
+    }
+
+    for (i = 0; i < n->outstanding_aers; i++) {
+        NvmeSQueue *sq = &n->admin_sq;
+        NvmeRequest *req_from = n->aer_reqs[i];
+        NvmeRequest *req;
+
+        /*
+         * We use nvme_vmstate VMStateDescription to save/restore
+         * NvmeRequest structures, but tricky thing here is that
+         * memory for each n->aer_reqs[i] will be allocated separately
+         * during restore. It doesn't work for us. We need to take
+         * an existing NvmeRequest structure from SQ's req_list
+         * and fill it with data from the newly allocated one (req_from).
+         * Then, we can safely release allocated memory for it.
+         */
+
+        /* take an NvmeRequest struct from SQ */
+        req = QTAILQ_FIRST(&sq->req_list);
+        QTAILQ_REMOVE(&sq->req_list, req, entry);
+        QTAILQ_INSERT_TAIL(&sq->out_req_list, req, entry);
+        nvme_req_clear(req);
+
+        /* copy data from the source NvmeRequest */
+        req->status = req_from->status;
+        memcpy(&req->cqe, &req_from->cqe, sizeof(NvmeCqe));
+        memcpy(&req->cmd, &req_from->cmd, sizeof(NvmeCmd));
+
+        n->aer_reqs[i] = req;
+        g_free(req_from);
+    }
+
+    /*
+     * We need to attach namespaces (currently, only one namespace is
+     * supported for migration).
+     * This logic comes from nvme_start_ctrl().
+     */
+    for (i = 1; i <= NVME_MAX_NAMESPACES; i++) {
+        NvmeNamespace *ns = nvme_subsys_ns(n->subsys, i);
+
+        if (!ns || (!ns->params.shared && ns->ctrl != n)) {
+            continue;
+        }
+
+        if (nvme_csi_supported(n, ns->csi) && !ns->params.detached) {
+            if (!ns->attached || ns->params.shared) {
+                nvme_attach_ns(n, ns);
+            }
+        }
+    }
+
+    /* schedule SQ processing */
+    for (i = 0; i < n->num_queues; i++) {
+        NvmeSQueue *sq = n->sq[i];
+
+        if (!sq)
+            continue;
+
+        qemu_bh_schedule(sq->bh);
+    }
+
+    /*
+     * We ensured in pre_save() that cq->req_list was empty,
+     * so we don't need to schedule BH for CQ processing.
+     */
+
+    return true;
+}
+
+static const VMStateDescription nvme_vmstate_bar = {
+    .name = "nvme-bar",
+    .minimum_version_id = 1,
+    .version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT64(cap, NvmeBar),
+        VMSTATE_UINT32(vs, NvmeBar),
+        VMSTATE_UINT32(intms, NvmeBar),
+        VMSTATE_UINT32(intmc, NvmeBar),
+        VMSTATE_UINT32(cc, NvmeBar),
+        VMSTATE_UINT8_ARRAY(rsvd24, NvmeBar, 4),
+        VMSTATE_UINT32(csts, NvmeBar),
+        VMSTATE_UINT32(nssr, NvmeBar),
+        VMSTATE_UINT32(aqa, NvmeBar),
+        VMSTATE_UINT64(asq, NvmeBar),
+        VMSTATE_UINT64(acq, NvmeBar),
+        VMSTATE_UINT32(cmbloc, NvmeBar),
+        VMSTATE_UINT32(cmbsz, NvmeBar),
+        VMSTATE_UINT32(bpinfo, NvmeBar),
+        VMSTATE_UINT32(bprsel, NvmeBar),
+        VMSTATE_UINT64(bpmbl, NvmeBar),
+        VMSTATE_UINT64(cmbmsc, NvmeBar),
+        VMSTATE_UINT32(cmbsts, NvmeBar),
+        VMSTATE_UINT8_ARRAY(rsvd92, NvmeBar, 3492),
+        VMSTATE_UINT32(pmrcap, NvmeBar),
+        VMSTATE_UINT32(pmrctl, NvmeBar),
+        VMSTATE_UINT32(pmrsts, NvmeBar),
+        VMSTATE_UINT32(pmrebs, NvmeBar),
+        VMSTATE_UINT32(pmrswtp, NvmeBar),
+        VMSTATE_UINT32(pmrmscl, NvmeBar),
+        VMSTATE_UINT32(pmrmscu, NvmeBar),
+        VMSTATE_UINT8_ARRAY(css, NvmeBar, 484),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static const VMStateDescription nvme_vmstate_cqueue = {
+    .name = "nvme-cq",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT8(phase, NvmeCQueue),
+        VMSTATE_UINT16(cqid, NvmeCQueue),
+        VMSTATE_UINT16(irq_enabled, NvmeCQueue),
+        VMSTATE_UINT32(head, NvmeCQueue),
+        VMSTATE_UINT32(tail, NvmeCQueue),
+        VMSTATE_UINT32(vector, NvmeCQueue),
+        VMSTATE_UINT32(size, NvmeCQueue),
+        VMSTATE_UINT64(dma_addr, NvmeCQueue),
+        /* db_addr, ei_addr, etc will be recalculated */
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_squeue = {
+    .name = "nvme-sq",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT16(sqid, NvmeSQueue),
+        VMSTATE_UINT16(cqid, NvmeSQueue),
+        VMSTATE_UINT32(head, NvmeSQueue),
+        VMSTATE_UINT32(tail, NvmeSQueue),
+        VMSTATE_UINT32(size, NvmeSQueue),
+        VMSTATE_UINT64(dma_addr, NvmeSQueue),
+        /* db_addr, ei_addr, etc will be recalculated */
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_async_event_result = {
+    .name = "nvme-async-event-result",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT8(event_type, NvmeAerResult),
+        VMSTATE_UINT8(event_info, NvmeAerResult),
+        VMSTATE_UINT8(log_page, NvmeAerResult),
+        VMSTATE_UINT8(resv, NvmeAerResult),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_async_event = {
+    .name = "nvme-async-event",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_STRUCT(result, NvmeAsyncEvent, 0, nvme_vmstate_async_event_result, NvmeAerResult),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_cqe = {
+    .name = "nvme-cqe",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT32(result, NvmeCqe),
+        VMSTATE_UINT32(dw1, NvmeCqe),
+        VMSTATE_UINT16(sq_head, NvmeCqe),
+        VMSTATE_UINT16(sq_id, NvmeCqe),
+        VMSTATE_UINT16(cid, NvmeCqe),
+        VMSTATE_UINT16(status, NvmeCqe),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_cmd_dptr_sgl = {
+    .name = "nvme-request-cmd-dptr-sgl",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT64(addr, NvmeSglDescriptor),
+        VMSTATE_UINT32(len, NvmeSglDescriptor),
+        VMSTATE_UINT8_ARRAY(rsvd, NvmeSglDescriptor, 3),
+        VMSTATE_UINT8(type, NvmeSglDescriptor),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_cmd_dptr = {
+    .name = "nvme-request-cmd-dptr",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT64(prp1, NvmeCmdDptr),
+        VMSTATE_UINT64(prp2, NvmeCmdDptr),
+        VMSTATE_STRUCT(sgl, NvmeCmdDptr, 0, nvme_vmstate_cmd_dptr_sgl, NvmeSglDescriptor),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_cmd = {
+    .name = "nvme-request-cmd",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT8(opcode, NvmeCmd),
+        VMSTATE_UINT8(flags, NvmeCmd),
+        VMSTATE_UINT16(cid, NvmeCmd),
+        VMSTATE_UINT32(nsid, NvmeCmd),
+        VMSTATE_UINT64(res1, NvmeCmd),
+        VMSTATE_UINT64(mptr, NvmeCmd),
+        VMSTATE_STRUCT(dptr, NvmeCmd, 0, nvme_vmstate_cmd_dptr, NvmeCmdDptr),
+        VMSTATE_UINT32(cdw10, NvmeCmd),
+        VMSTATE_UINT32(cdw11, NvmeCmd),
+        VMSTATE_UINT32(cdw12, NvmeCmd),
+        VMSTATE_UINT32(cdw13, NvmeCmd),
+        VMSTATE_UINT32(cdw14, NvmeCmd),
+        VMSTATE_UINT32(cdw15, NvmeCmd),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static const VMStateDescription nvme_vmstate_request = {
+    .name = "nvme-request",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT16(status, NvmeRequest),
+        VMSTATE_STRUCT(cqe, NvmeRequest, 0, nvme_vmstate_cqe, NvmeCqe),
+        VMSTATE_STRUCT(cmd, NvmeRequest, 0, nvme_vmstate_cmd, NvmeCmd),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription nvme_vmstate = {
     .name = "nvme",
-    .unmigratable = 1,
+    .minimum_version_id = 1,
+    .version_id = 1,
+    .pre_save_errp = nvme_ctrl_pre_save,
+    .post_load_errp = nvme_ctrl_post_load,
+    .fields = (const VMStateField[]) {
+        VMSTATE_PCI_DEVICE(parent_obj, NvmeCtrl),
+        VMSTATE_MSIX(parent_obj, NvmeCtrl),
+        VMSTATE_STRUCT(bar, NvmeCtrl, 0, nvme_vmstate_bar, NvmeBar),
+
+        VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT32_ALLOC(
+            sq, NvmeCtrl, num_queues, 0, nvme_vmstate_squeue, NvmeSQueue),
+        VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT32_ALLOC(
+            cq, NvmeCtrl, num_queues, 0, nvme_vmstate_cqueue, NvmeCQueue),
+
+        VMSTATE_BOOL(qs_created, NvmeCtrl),
+        VMSTATE_UINT32(page_size, NvmeCtrl),
+        VMSTATE_UINT16(page_bits, NvmeCtrl),
+        VMSTATE_UINT16(max_prp_ents, NvmeCtrl),
+        VMSTATE_UINT32(max_q_ents, NvmeCtrl),
+        VMSTATE_UINT8(outstanding_aers, NvmeCtrl),
+        VMSTATE_UINT32(irq_status, NvmeCtrl),
+        VMSTATE_INT32(cq_pending, NvmeCtrl),
+
+        VMSTATE_UINT64(host_timestamp, NvmeCtrl),
+        VMSTATE_UINT64(timestamp_set_qemu_clock_ms, NvmeCtrl),
+        VMSTATE_UINT64(starttime_ms, NvmeCtrl),
+        VMSTATE_UINT16(temperature, NvmeCtrl),
+        VMSTATE_UINT8(smart_critical_warning, NvmeCtrl),
+
+        VMSTATE_UINT32(conf_msix_qsize, NvmeCtrl),
+        VMSTATE_UINT32(conf_ioqpairs, NvmeCtrl),
+        VMSTATE_UINT64(dbbuf_dbs, NvmeCtrl),
+        VMSTATE_UINT64(dbbuf_eis, NvmeCtrl),
+        VMSTATE_BOOL(dbbuf_enabled, NvmeCtrl),
+
+        VMSTATE_UINT8(aer_mask, NvmeCtrl),
+        VMSTATE_VARRAY_OF_POINTER_TO_STRUCT_UINT8_ALLOC(
+            aer_reqs, NvmeCtrl, outstanding_aers, 0, nvme_vmstate_request, NvmeRequest),
+        VMSTATE_QTAILQ_V(aer_queue, NvmeCtrl, 1, nvme_vmstate_async_event,
+                         NvmeAsyncEvent, entry),
+        VMSTATE_INT32(aer_queued, NvmeCtrl),
+
+        VMSTATE_END_OF_LIST()
+    },
 };
 
 static void nvme_class_init(ObjectClass *oc, const void *data)
hw/nvme/nvme.h +2 -0
index 457b6637249..9c5f53c688c 100644
@@ -638,6 +638,7 @@ typedef struct NvmeCtrl {
 
     NvmeNamespace   namespace;
     NvmeNamespace   *namespaces[NVME_MAX_NAMESPACES + 1];
+    uint32_t        num_queues;
     NvmeSQueue      **sq;
     NvmeCQueue      **cq;
     NvmeSQueue      admin_sq;
@@ -669,6 +670,7 @@ typedef struct NvmeCtrl {
 
     /* Migration-related stuff */
     Error *migration_blocker;
+    bool stop_processing_sq;
 } NvmeCtrl;
 
 typedef enum NvmeResetType {
hw/nvme/trace-events +11 -0
index 6be0bfa1c1f..8e5544e0008 100644
@@ -7,6 +7,17 @@ pci_nvme_dbbuf_config(uint64_t dbs_addr, uint64_t eis_addr) "dbs_addr=0x%"PRIx64
 pci_nvme_map_addr(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64""
 pci_nvme_map_addr_cmb(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64""
 pci_nvme_map_prp(uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d"
+pci_nvme_pre_save_enter(void *n) "n=%p"
+pci_nvme_pre_save_ns_drain(void *n, int i) "n=%p i=%d"
+pci_nvme_pre_save_sq_out_req_drain_wait(void *n, int i, uint32_t head, uint32_t tail, uint32_t size) "n=%p i=%d head=0x%"PRIx32" tail=0x%"PRIx32" size=0x%"PRIx32""
+pci_nvme_pre_save_sq_out_req_drain_wait_end(void *n, int i, uint32_t head, uint32_t tail) "n=%p i=%d head=0x%"PRIx32" tail=0x%"PRIx32""
+pci_nvme_pre_save_cq_req_drain_wait(void *n, int i, uint32_t head, uint32_t tail, uint32_t size) "n=%p i=%d head=0x%"PRIx32" tail=0x%"PRIx32" size=0x%"PRIx32""
+pci_nvme_pre_save_cq_req_drain_wait_end(void *n, int i, uint32_t head, uint32_t tail) "n=%p i=%d head=0x%"PRIx32" tail=0x%"PRIx32""
+pci_nvme_pre_save_aer(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
+pci_nvme_post_load_enter(void *n) "n=%p"
+pci_nvme_post_load_restore_cq(void *n, int i, uint32_t head, uint32_t tail, uint32_t size) "n=%p i=%d head=0x%"PRIx32" tail=0x%"PRIx32" size=0x%"PRIx32""
+pci_nvme_post_load_restore_sq(void *n, int i, uint32_t head, uint32_t tail, uint32_t size) "n=%p i=%d head=0x%"PRIx32" tail=0x%"PRIx32" size=0x%"PRIx32""
+pci_nvme_post_load_aer(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
 pci_nvme_map_sgl(uint8_t typ, uint64_t len) "type 0x%"PRIx8" len %"PRIu64""
 pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" nsid 0x%"PRIx32" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'"
 pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'"
Signature · 1 line
2.47.3