All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kirti Wankhede <kwankhede@nvidia.com>
To: <alex.williamson@redhat.com>, <cjia@nvidia.com>
Cc: cohuck@redhat.com, zhi.wang.linux@gmail.com, aik@ozlabs.ru,
	Zhengxiao.zx@Alibaba-inc.com, shuangtai.tst@alibaba-inc.com,
	qemu-devel@nongnu.org, peterx@redhat.com,
	Kirti Wankhede <kwankhede@nvidia.com>,
	eauger@redhat.com, yi.l.liu@intel.com, quintela@redhat.com,
	ziye.yang@intel.com, armbru@redhat.com, mlevitsk@redhat.com,
	pasic@linux.ibm.com, felipe@nutanix.com, zhi.a.wang@intel.com,
	mcrossley@nvidia.com, kevin.tian@intel.com, yan.y.zhao@intel.com,
	dgilbert@redhat.com, changpeng.liu@intel.com,
	eskultet@redhat.com, Ken.Xue@amd.com,
	jonathan.davies@nutanix.com, pbonzini@redhat.com,
	dnigam@nvidia.com
Subject: [PATCH v27 09/17] vfio: Add load state functions to SaveVMHandlers
Date: Thu, 22 Oct 2020 16:41:59 +0530	[thread overview]
Message-ID: <1603365127-14202-10-git-send-email-kwankhede@nvidia.com> (raw)
In-Reply-To: <1603365127-14202-1-git-send-email-kwankhede@nvidia.com>

Sequence  during _RESUMING device state:
While data for this device is available, repeat below steps:
a. read data_offset from where user application should write data.
b. write data of data_size to migration region from data_offset.
c. write data_size which indicates vendor driver that data is written in
   staging buffer.

For user, data is opaque. User should write data in the same order as
received.

Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 hw/vfio/migration.c  | 192 +++++++++++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/trace-events |   3 +
 2 files changed, 195 insertions(+)

diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 5506cef15d88..46d05d230e2a 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -257,6 +257,77 @@ static int vfio_save_buffer(QEMUFile *f, VFIODevice *vbasedev, uint64_t *size)
     return ret;
 }
 
+static int vfio_load_buffer(QEMUFile *f, VFIODevice *vbasedev,
+                            uint64_t data_size)
+{
+    VFIORegion *region = &vbasedev->migration->region;
+    uint64_t data_offset = 0, size, report_size;
+    int ret;
+
+    do {
+        ret = vfio_mig_read(vbasedev, &data_offset, sizeof(data_offset),
+                      region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_offset));
+        if (ret < 0) {
+            return ret;
+        }
+
+        if (data_offset + data_size > region->size) {
+            /*
+             * If data_size is greater than the data section of migration region
+             * then iterate the write buffer operation. This case can occur if
+             * size of migration region at destination is smaller than size of
+             * migration region at source.
+             */
+            report_size = size = region->size - data_offset;
+            data_size -= size;
+        } else {
+            report_size = size = data_size;
+            data_size = 0;
+        }
+
+        trace_vfio_load_state_device_data(vbasedev->name, data_offset, size);
+
+        while (size) {
+            void *buf;
+            uint64_t sec_size;
+            bool buf_alloc = false;
+
+            buf = get_data_section_size(region, data_offset, size, &sec_size);
+
+            if (!buf) {
+                buf = g_try_malloc(sec_size);
+                if (!buf) {
+                    error_report("%s: Error allocating buffer ", __func__);
+                    return -ENOMEM;
+                }
+                buf_alloc = true;
+            }
+
+            qemu_get_buffer(f, buf, sec_size);
+
+            if (buf_alloc) {
+                ret = vfio_mig_write(vbasedev, buf, sec_size,
+                        region->fd_offset + data_offset);
+                g_free(buf);
+
+                if (ret < 0) {
+                    return ret;
+                }
+            }
+            size -= sec_size;
+            data_offset += sec_size;
+        }
+
+        ret = vfio_mig_write(vbasedev, &report_size, sizeof(report_size),
+                        region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_size));
+        if (ret < 0) {
+            return ret;
+        }
+    } while (data_size);
+
+    return 0;
+}
+
 static int vfio_update_pending(VFIODevice *vbasedev)
 {
     VFIOMigration *migration = vbasedev->migration;
@@ -293,6 +364,33 @@ static int vfio_save_device_config_state(QEMUFile *f, void *opaque)
     return qemu_file_get_error(f);
 }
 
+static int vfio_load_device_config_state(QEMUFile *f, void *opaque)
+{
+    VFIODevice *vbasedev = opaque;
+    uint64_t data;
+
+    if (vbasedev->ops && vbasedev->ops->vfio_load_config) {
+        int ret;
+
+        ret = vbasedev->ops->vfio_load_config(vbasedev, f);
+        if (ret) {
+            error_report("%s: Failed to load device config space",
+                         vbasedev->name);
+            return ret;
+        }
+    }
+
+    data = qemu_get_be64(f);
+    if (data != VFIO_MIG_FLAG_END_OF_STATE) {
+        error_report("%s: Failed loading device config space, "
+                     "end flag incorrect 0x%"PRIx64, vbasedev->name, data);
+        return -EINVAL;
+    }
+
+    trace_vfio_load_device_config_state(vbasedev->name);
+    return qemu_file_get_error(f);
+}
+
 /* ---------------------------------------------------------------------- */
 
 static int vfio_save_setup(QEMUFile *f, void *opaque)
@@ -477,12 +575,106 @@ static int vfio_save_complete_precopy(QEMUFile *f, void *opaque)
     return ret;
 }
 
+static int vfio_load_setup(QEMUFile *f, void *opaque)
+{
+    VFIODevice *vbasedev = opaque;
+    VFIOMigration *migration = vbasedev->migration;
+    int ret = 0;
+
+    if (migration->region.mmaps) {
+        ret = vfio_region_mmap(&migration->region);
+        if (ret) {
+            error_report("%s: Failed to mmap VFIO migration region %d: %s",
+                         vbasedev->name, migration->region.nr,
+                         strerror(-ret));
+            error_report("%s: Falling back to slow path", vbasedev->name);
+        }
+    }
+
+    ret = vfio_migration_set_state(vbasedev, ~VFIO_DEVICE_STATE_MASK,
+                                   VFIO_DEVICE_STATE_RESUMING);
+    if (ret) {
+        error_report("%s: Failed to set state RESUMING", vbasedev->name);
+        if (migration->region.mmaps) {
+            vfio_region_unmap(&migration->region);
+        }
+    }
+    return ret;
+}
+
+static int vfio_load_cleanup(void *opaque)
+{
+    vfio_save_cleanup(opaque);
+    return 0;
+}
+
+static int vfio_load_state(QEMUFile *f, void *opaque, int version_id)
+{
+    VFIODevice *vbasedev = opaque;
+    int ret = 0;
+    uint64_t data;
+
+    data = qemu_get_be64(f);
+    while (data != VFIO_MIG_FLAG_END_OF_STATE) {
+
+        trace_vfio_load_state(vbasedev->name, data);
+
+        switch (data) {
+        case VFIO_MIG_FLAG_DEV_CONFIG_STATE:
+        {
+            ret = vfio_load_device_config_state(f, opaque);
+            if (ret) {
+                return ret;
+            }
+            break;
+        }
+        case VFIO_MIG_FLAG_DEV_SETUP_STATE:
+        {
+            data = qemu_get_be64(f);
+            if (data == VFIO_MIG_FLAG_END_OF_STATE) {
+                return ret;
+            } else {
+                error_report("%s: SETUP STATE: EOS not found 0x%"PRIx64,
+                             vbasedev->name, data);
+                return -EINVAL;
+            }
+            break;
+        }
+        case VFIO_MIG_FLAG_DEV_DATA_STATE:
+        {
+            uint64_t data_size = qemu_get_be64(f);
+
+            if (data_size) {
+                ret = vfio_load_buffer(f, vbasedev, data_size);
+                if (ret < 0) {
+                    return ret;
+                }
+            }
+            break;
+        }
+        default:
+            error_report("%s: Unknown tag 0x%"PRIx64, vbasedev->name, data);
+            return -EINVAL;
+        }
+
+        data = qemu_get_be64(f);
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            return ret;
+        }
+    }
+    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,
+    .load_setup = vfio_load_setup,
+    .load_cleanup = vfio_load_cleanup,
+    .load_state = vfio_load_state,
 };
 
 /* ---------------------------------------------------------------------- */
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 9f5712dab1ea..4804cc266d44 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -159,3 +159,6 @@ vfio_save_device_config_state(const char *name) " (%s)"
 vfio_save_pending(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
 vfio_save_iterate(const char *name, int data_size) " (%s) data_size %d"
 vfio_save_complete_precopy(const char *name) " (%s)"
+vfio_load_device_config_state(const char *name) " (%s)"
+vfio_load_state(const char *name, uint64_t data) " (%s) data 0x%"PRIx64
+vfio_load_state_device_data(const char *name, uint64_t data_offset, uint64_t data_size) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64
-- 
2.7.0



  parent reply	other threads:[~2020-10-22 11:56 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-22 11:11 [PATCH v27 00/17] Add migration support for VFIO devices Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 01/17] vfio: Add function to unmap VFIO region Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 02/17] vfio: Add vfio_get_object callback to VFIODeviceOps Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 03/17] vfio: Add save and load functions for VFIO PCI devices Kirti Wankhede
2020-10-22 14:06   ` Alex Williamson
2020-10-22 15:52     ` Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 04/17] vfio: Add migration region initialization and finalize function Kirti Wankhede
2020-10-22 14:22   ` Alex Williamson
2020-10-22 16:16     ` Kirti Wankhede
2020-10-23 11:17   ` Cornelia Huck
2020-10-22 11:11 ` [PATCH v27 05/17] vfio: Add VM state change handler to know state of VM Kirti Wankhede
2020-10-22 16:35   ` Alex Williamson
2020-10-22 17:41     ` Kirti Wankhede
2020-10-22 18:29       ` Alex Williamson
2020-10-22 11:11 ` [PATCH v27 06/17] vfio: Add migration state change notifier Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 07/17] vfio: Register SaveVMHandlers for VFIO device Kirti Wankhede
2020-10-22 18:51   ` Alex Williamson
2020-10-23  7:12     ` Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 08/17] vfio: Add save state functions to SaveVMHandlers Kirti Wankhede
2020-10-22 11:11 ` Kirti Wankhede [this message]
2020-10-22 19:50   ` [PATCH v27 09/17] vfio: Add load " Alex Williamson
2020-10-23  9:59     ` Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 10/17] memory: Set DIRTY_MEMORY_MIGRATION when IOMMU is enabled Kirti Wankhede
2020-10-22 19:52   ` Alex Williamson
2020-10-22 11:12 ` [PATCH v27 11/17] vfio: Get migration capability flags for container Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 12/17] vfio: Add function to start and stop dirty pages tracking Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 13/17] vfio: Add vfio_listener_log_sync to mark dirty pages Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 14/17] vfio: Dirty page tracking when vIOMMU is enabled Kirti Wankhede
2020-10-22 20:37   ` Alex Williamson
2020-10-23  7:55     ` Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 15/17] vfio: Add ioctl to get dirty pages bitmap during dma unmap Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 16/17] vfio: Make vfio-pci device migration capable Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 17/17] qapi: Add VFIO devices migration stats in Migration stats Kirti Wankhede
2020-10-22 22:18   ` Alex Williamson
2020-10-23 10:21     ` Kirti Wankhede
2020-10-22 21:28 ` [PATCH v27 00/17] Add migration support for VFIO devices 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=1603365127-14202-10-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=armbru@redhat.com \
    --cc=changpeng.liu@intel.com \
    --cc=cjia@nvidia.com \
    --cc=cohuck@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=dnigam@nvidia.com \
    --cc=eauger@redhat.com \
    --cc=eskultet@redhat.com \
    --cc=felipe@nutanix.com \
    --cc=jonathan.davies@nutanix.com \
    --cc=kevin.tian@intel.com \
    --cc=mcrossley@nvidia.com \
    --cc=mlevitsk@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --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=zhi.wang.linux@gmail.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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.