QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Kirti Wankhede <kwankhede@nvidia.com>
To: <alex.williamson@redhat.com>, <cjia@nvidia.com>
Cc: Zhengxiao.zx@Alibaba-inc.com, kevin.tian@intel.com,
	yi.l.liu@intel.com, yan.y.zhao@intel.com, eskultet@redhat.com,
	ziye.yang@intel.com, qemu-devel@nongnu.org, cohuck@redhat.com,
	shuangtai.tst@alibaba-inc.com, dgilbert@redhat.com,
	zhi.a.wang@intel.com, mlevitsk@redhat.com, pasic@linux.ibm.com,
	aik@ozlabs.ru, Kirti Wankhede <kwankhede@nvidia.com>,
	eauger@redhat.com, felipe@nutanix.com,
	jonathan.davies@nutanix.com, changpeng.liu@intel.com,
	Ken.Xue@amd.com
Subject: [PATCH v16 QEMU 09/16] vfio: Add save state functions to SaveVMHandlers
Date: Wed, 25 Mar 2020 02:39:07 +0530
Message-ID: <1585084154-29461-10-git-send-email-kwankhede@nvidia.com> (raw)
In-Reply-To: <1585084154-29461-1-git-send-email-kwankhede@nvidia.com>

Added .save_live_pending, .save_live_iterate and .save_live_complete_precopy
functions. These functions handles pre-copy and stop-and-copy phase.

In _SAVING|_RUNNING device state or pre-copy phase:
- read pending_bytes. If pending_bytes > 0, go through below steps.
- read data_offset - indicates kernel driver to write data to staging
  buffer.
- read data_size - amount of data in bytes written by vendor driver in
  migration region.
- read data_size bytes of data from data_offset in the migration region.
- Write data packet to file stream as below:
{VFIO_MIG_FLAG_DEV_DATA_STATE, data_size, actual data,
VFIO_MIG_FLAG_END_OF_STATE }

In _SAVING device state or stop-and-copy phase
a. read config space of device and save to migration file stream. This
   doesn't need to be from vendor driver. Any other special config state
   from driver can be saved as data in following iteration.
b. read pending_bytes. If pending_bytes > 0, go through below steps.
c. read data_offset - indicates kernel driver to write data to staging
   buffer.
d. read data_size - amount of data in bytes written by vendor driver in
   migration region.
e. read data_size bytes of data from data_offset in the migration region.
f. Write data packet as below:
   {VFIO_MIG_FLAG_DEV_DATA_STATE, data_size, actual data}
g. iterate through steps b to f while (pending_bytes > 0)
h. Write {VFIO_MIG_FLAG_END_OF_STATE}

When data region is mapped, its user's responsibility to read data from
data_offset of data_size before moving to next steps.

Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
---
 hw/vfio/migration.c           | 245 +++++++++++++++++++++++++++++++++++++++++-
 hw/vfio/trace-events          |   6 ++
 include/hw/vfio/vfio-common.h |   1 +
 3 files changed, 251 insertions(+), 1 deletion(-)

diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 033f76526e49..ecbeed5182c2 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -138,6 +138,137 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t mask,
     return 0;
 }
 
+static void *find_data_region(VFIORegion *region,
+                              uint64_t data_offset,
+                              uint64_t data_size)
+{
+    void *ptr = NULL;
+    int i;
+
+    for (i = 0; i < region->nr_mmaps; i++) {
+        if ((data_offset >= region->mmaps[i].offset) &&
+            (data_offset < region->mmaps[i].offset + region->mmaps[i].size) &&
+            (data_size <= region->mmaps[i].size)) {
+            ptr = region->mmaps[i].mmap + (data_offset -
+                                           region->mmaps[i].offset);
+            break;
+        }
+    }
+    return ptr;
+}
+
+static int vfio_save_buffer(QEMUFile *f, VFIODevice *vbasedev)
+{
+    VFIOMigration *migration = vbasedev->migration;
+    VFIORegion *region = &migration->region;
+    uint64_t data_offset = 0, data_size = 0;
+    int ret;
+
+    ret = pread(vbasedev->fd, &data_offset, sizeof(data_offset),
+                region->fd_offset + offsetof(struct vfio_device_migration_info,
+                                             data_offset));
+    if (ret != sizeof(data_offset)) {
+        error_report("%s: Failed to get migration buffer data offset %d",
+                     vbasedev->name, ret);
+        return -EINVAL;
+    }
+
+    ret = pread(vbasedev->fd, &data_size, sizeof(data_size),
+                region->fd_offset + offsetof(struct vfio_device_migration_info,
+                                             data_size));
+    if (ret != sizeof(data_size)) {
+        error_report("%s: Failed to get migration buffer data size %d",
+                     vbasedev->name, ret);
+        return -EINVAL;
+    }
+
+    if (data_size > 0) {
+        void *buf = NULL;
+        bool buffer_mmaped;
+
+        if (region->mmaps) {
+            buf = find_data_region(region, data_offset, data_size);
+        }
+
+        buffer_mmaped = (buf != NULL) ? true : false;
+
+        if (!buffer_mmaped) {
+            buf = g_try_malloc0(data_size);
+            if (!buf) {
+                error_report("%s: Error allocating buffer ", __func__);
+                return -ENOMEM;
+            }
+
+            ret = pread(vbasedev->fd, buf, data_size,
+                        region->fd_offset + data_offset);
+            if (ret != data_size) {
+                error_report("%s: Failed to get migration data %d",
+                             vbasedev->name, ret);
+                g_free(buf);
+                return -EINVAL;
+            }
+        }
+
+        qemu_put_be64(f, data_size);
+        qemu_put_buffer(f, buf, data_size);
+
+        if (!buffer_mmaped) {
+            g_free(buf);
+        }
+    } else {
+        qemu_put_be64(f, data_size);
+    }
+
+    trace_vfio_save_buffer(vbasedev->name, data_offset, data_size,
+                           migration->pending_bytes);
+
+    ret = qemu_file_get_error(f);
+    if (ret) {
+        return ret;
+    }
+
+    return data_size;
+}
+
+static int vfio_update_pending(VFIODevice *vbasedev)
+{
+    VFIOMigration *migration = vbasedev->migration;
+    VFIORegion *region = &migration->region;
+    uint64_t pending_bytes = 0;
+    int ret;
+
+    ret = pread(vbasedev->fd, &pending_bytes, sizeof(pending_bytes),
+                region->fd_offset + offsetof(struct vfio_device_migration_info,
+                                             pending_bytes));
+    if ((ret < 0) || (ret != sizeof(pending_bytes))) {
+        error_report("%s: Failed to get pending bytes %d",
+                     vbasedev->name, ret);
+        migration->pending_bytes = 0;
+        return (ret < 0) ? ret : -EINVAL;
+    }
+
+    migration->pending_bytes = pending_bytes;
+    trace_vfio_update_pending(vbasedev->name, pending_bytes);
+    return 0;
+}
+
+static int vfio_save_device_config_state(QEMUFile *f, void *opaque)
+{
+    VFIODevice *vbasedev = opaque;
+
+    qemu_put_be64(f, VFIO_MIG_FLAG_DEV_CONFIG_STATE);
+
+    if (vbasedev->ops && vbasedev->ops->vfio_save_config) {
+        vbasedev->ops->vfio_save_config(vbasedev, f);
+    }
+
+    qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
+
+    trace_vfio_save_device_config_state(vbasedev->name);
+
+    return qemu_file_get_error(f);
+}
+
 /* ---------------------------------------------------------------------- */
 
 static int vfio_save_setup(QEMUFile *f, void *opaque)
@@ -154,7 +285,7 @@ static int vfio_save_setup(QEMUFile *f, void *opaque)
         qemu_mutex_unlock_iothread();
         if (ret) {
             error_report("%s: Failed to mmap VFIO migration region %d: %s",
-                         vbasedev->name, migration->region.index,
+                         vbasedev->name, migration->region.nr,
                          strerror(-ret));
             return ret;
         }
@@ -194,9 +325,121 @@ static void vfio_save_cleanup(void *opaque)
     trace_vfio_save_cleanup(vbasedev->name);
 }
 
+static void vfio_save_pending(QEMUFile *f, void *opaque,
+                              uint64_t threshold_size,
+                              uint64_t *res_precopy_only,
+                              uint64_t *res_compatible,
+                              uint64_t *res_postcopy_only)
+{
+    VFIODevice *vbasedev = opaque;
+    VFIOMigration *migration = vbasedev->migration;
+    int ret;
+
+    ret = vfio_update_pending(vbasedev);
+    if (ret) {
+        return;
+    }
+
+    *res_precopy_only += migration->pending_bytes;
+
+    trace_vfio_save_pending(vbasedev->name, *res_precopy_only,
+                            *res_postcopy_only, *res_compatible);
+}
+
+static int vfio_save_iterate(QEMUFile *f, void *opaque)
+{
+    VFIODevice *vbasedev = opaque;
+    int ret, data_size;
+
+    qemu_put_be64(f, VFIO_MIG_FLAG_DEV_DATA_STATE);
+
+    data_size = vfio_save_buffer(f, vbasedev);
+
+    if (data_size < 0) {
+        error_report("%s: vfio_save_buffer failed %s", vbasedev->name,
+                     strerror(errno));
+        return data_size;
+    }
+
+    qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
+
+    ret = qemu_file_get_error(f);
+    if (ret) {
+        return ret;
+    }
+
+    trace_vfio_save_iterate(vbasedev->name, data_size);
+    if (data_size == 0) {
+        /* indicates data finished, goto complete phase */
+        return 1;
+    }
+
+    return 0;
+}
+
+static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
+{
+    VFIODevice *vbasedev = opaque;
+    VFIOMigration *migration = vbasedev->migration;
+    int ret;
+
+    ret = vfio_migration_set_state(vbasedev, ~VFIO_DEVICE_STATE_RUNNING,
+                                   VFIO_DEVICE_STATE_SAVING);
+    if (ret) {
+        error_report("%s: Failed to set state STOP and SAVING",
+                     vbasedev->name);
+        return ret;
+    }
+
+    ret = vfio_save_device_config_state(f, opaque);
+    if (ret) {
+        return ret;
+    }
+
+    ret = vfio_update_pending(vbasedev);
+    if (ret) {
+        return ret;
+    }
+
+    while (migration->pending_bytes > 0) {
+        qemu_put_be64(f, VFIO_MIG_FLAG_DEV_DATA_STATE);
+        ret = vfio_save_buffer(f, vbasedev);
+        if (ret < 0) {
+            error_report("%s: Failed to save buffer", vbasedev->name);
+            return ret;
+        } else if (ret == 0) {
+            break;
+        }
+
+        ret = vfio_update_pending(vbasedev);
+        if (ret) {
+            return ret;
+        }
+    }
+
+    qemu_put_be64(f, VFIO_MIG_FLAG_END_OF_STATE);
+
+    ret = qemu_file_get_error(f);
+    if (ret) {
+        return ret;
+    }
+
+    ret = vfio_migration_set_state(vbasedev, ~VFIO_DEVICE_STATE_SAVING, 0);
+    if (ret) {
+        error_report("%s: Failed to set state STOPPED", vbasedev->name);
+        return ret;
+    }
+
+    trace_vfio_save_complete_precopy(vbasedev->name);
+    return ret;
+}
+
 static SaveVMHandlers savevm_vfio_handlers = {
     .save_setup = vfio_save_setup,
     .save_cleanup = vfio_save_cleanup,
+    .save_live_pending = vfio_save_pending,
+    .save_live_iterate = vfio_save_iterate,
+    .save_live_complete_precopy = vfio_save_complete_precopy,
 };
 
 /* ---------------------------------------------------------------------- */
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 4bb43f18f315..bdf40ba368c7 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -151,3 +151,9 @@ vfio_vmstate_change(char *name, int running, const char *reason, uint32_t dev_st
 vfio_migration_state_notifier(char *name, int state) " (%s) state %d"
 vfio_save_setup(char *name) " (%s)"
 vfio_save_cleanup(char *name) " (%s)"
+vfio_save_buffer(char *name, uint64_t data_offset, uint64_t data_size, uint64_t pending) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64" pending 0x%"PRIx64
+vfio_update_pending(char *name, uint64_t pending) " (%s) pending 0x%"PRIx64
+vfio_save_device_config_state(char *name) " (%s)"
+vfio_save_pending(char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
+vfio_save_iterate(char *name, int data_size) " (%s) data_size %d"
+vfio_save_complete_precopy(char *name) " (%s)"
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 28f55f66d019..c78033e4149d 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -60,6 +60,7 @@ typedef struct VFIORegion {
 
 typedef struct VFIOMigration {
     VFIORegion region;
+    uint64_t pending_bytes;
 } VFIOMigration;
 
 typedef struct VFIOAddressSpace {
-- 
2.7.0



  parent reply index

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-24 21:08 [PATCH v16 QEMU 00/16] Add migration support for VFIO devices Kirti Wankhede
2020-03-24 21:08 ` [PATCH v16 QEMU 01/16] vfio: KABI for migration interface - Kernel header placeholder Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 02/16] vfio: Add function to unmap VFIO region Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 03/16] vfio: Add vfio_get_object callback to VFIODeviceOps Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 04/16] vfio: Add save and load functions for VFIO PCI devices Kirti Wankhede
2020-03-25 19:56   ` Alex Williamson
2020-03-26 17:29     ` Dr. David Alan Gilbert
2020-03-26 17:38       ` Alex Williamson
2020-05-04 23:18     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-06  6:11         ` Yan Zhao
2020-05-06 19:48           ` Kirti Wankhede
2020-05-06 20:03             ` Alex Williamson
2020-05-07  5:40               ` Kirti Wankhede
2020-05-07 18:14                 ` Alex Williamson
2020-03-26 17:46   ` Dr. David Alan Gilbert
2020-05-04 23:19     ` Kirti Wankhede
2020-04-07  4:10   ` Longpeng (Mike, Cloud Infrastructure Service Product Dept.)
2020-05-04 23:21     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 05/16] vfio: Add migration region initialization and finalize function Kirti Wankhede
2020-03-26 17:52   ` Dr. David Alan Gilbert
2020-05-04 23:19     ` Kirti Wankhede
2020-05-19 19:32       ` Dr. David Alan Gilbert
2020-03-24 21:09 ` [PATCH v16 QEMU 06/16] vfio: Add VM state change handler to know state of VM Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 07/16] vfio: Add migration state change notifier Kirti Wankhede
2020-04-01 11:27   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 08/16] vfio: Register SaveVMHandlers for VFIO device Kirti Wankhede
2020-03-25 21:02   ` Alex Williamson
2020-05-04 23:19     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-06  6:38         ` Yan Zhao
2020-05-06  9:58           ` Cornelia Huck
2020-05-06 16:53             ` Dr. David Alan Gilbert
2020-05-06 19:30               ` Kirti Wankhede
2020-05-07  6:37                 ` Cornelia Huck
2020-05-07 20:29                 ` Alex Williamson
2020-04-01 17:36   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` Kirti Wankhede [this message]
2020-03-25 22:03   ` [PATCH v16 QEMU 09/16] vfio: Add save state functions to SaveVMHandlers Alex Williamson
2020-05-04 23:18     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-11  9:53         ` Kirti Wankhede
2020-05-11 15:59           ` Alex Williamson
2020-05-12  2:06           ` Yan Zhao
2020-05-09  5:31   ` Yan Zhao
2020-05-11 10:22     ` Kirti Wankhede
2020-05-12  0:50       ` Yan Zhao
2020-03-24 21:09 ` [PATCH v16 QEMU 10/16] vfio: Add load " Kirti Wankhede
2020-03-25 22:36   ` Alex Williamson
2020-04-01 18:58   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 11/16] iommu: add callback to get address limit IOMMU supports Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 12/16] memory: Set DIRTY_MEMORY_MIGRATION when IOMMU is enabled Kirti Wankhede
2020-04-01 19:00   ` Dr. David Alan Gilbert
2020-04-01 19:42     ` Alex Williamson
2020-03-24 21:09 ` [PATCH v16 QEMU 13/16] vfio: Add function to start and stop dirty pages tracking Kirti Wankhede
2020-03-26 19:10   ` Alex Williamson
2020-05-04 23:20     ` Kirti Wankhede
2020-04-01 19:03   ` Dr. David Alan Gilbert
2020-05-04 23:21     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 14/16] vfio: Add vfio_listener_log_sync to mark dirty pages Kirti Wankhede
2020-03-25  2:19   ` Yan Zhao
2020-03-26 19:46   ` Alex Williamson
2020-04-01 19:08     ` Dr. David Alan Gilbert
2020-04-01  5:50   ` Yan Zhao
2020-04-03 20:11     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 15/16] vfio: Add ioctl to get dirty pages bitmap during dma unmap Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 16/16] vfio: Make vfio-pci device migration capable Kirti Wankhede
2020-03-24 23:36 ` [PATCH v16 QEMU 00/16] Add migration support for VFIO devices no-reply
2020-03-31 18:34 ` Alex Williamson
2020-04-01  6:41   ` Yan Zhao
2020-04-01 18:34     ` Alex Williamson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1585084154-29461-10-git-send-email-kwankhede@nvidia.com \
    --to=kwankhede@nvidia.com \
    --cc=Ken.Xue@amd.com \
    --cc=Zhengxiao.zx@Alibaba-inc.com \
    --cc=aik@ozlabs.ru \
    --cc=alex.williamson@redhat.com \
    --cc=changpeng.liu@intel.com \
    --cc=cjia@nvidia.com \
    --cc=cohuck@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=eauger@redhat.com \
    --cc=eskultet@redhat.com \
    --cc=felipe@nutanix.com \
    --cc=jonathan.davies@nutanix.com \
    --cc=kevin.tian@intel.com \
    --cc=mlevitsk@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=shuangtai.tst@alibaba-inc.com \
    --cc=yan.y.zhao@intel.com \
    --cc=yi.l.liu@intel.com \
    --cc=zhi.a.wang@intel.com \
    --cc=ziye.yang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git