QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Alex Williamson <alex.williamson@redhat.com>
To: qemu-devel@nongnu.org
Cc: Kirti Wankhede <kwankhede@nvidia.com>, Neo Jia <cjia@nvidia.com>
Subject: [PULL 13/32] vfio: Add vfio_listener_log_sync to mark dirty pages
Date: Mon, 26 Oct 2020 13:34:16 -0600
Message-ID: <160374085615.22414.9118278258571519417.stgit@gimli.home> (raw)
In-Reply-To: <160374054442.22414.10832953989449611268.stgit@gimli.home>

From: Kirti Wankhede <kwankhede@nvidia.com>

vfio_listener_log_sync gets list of dirty pages from container using
VFIO_IOMMU_GET_DIRTY_BITMAP ioctl and mark those pages dirty when all
devices are stopped and saving state.
Return early for the RAM block section of mapped MMIO region.

Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 hw/vfio/common.c     |  116 ++++++++++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/trace-events |    1 
 2 files changed, 117 insertions(+)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index d4959c036dd1..2634387df948 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -29,6 +29,7 @@
 #include "hw/vfio/vfio.h"
 #include "exec/address-spaces.h"
 #include "exec/memory.h"
+#include "exec/ram_addr.h"
 #include "hw/hw.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
@@ -37,6 +38,7 @@
 #include "sysemu/reset.h"
 #include "trace.h"
 #include "qapi/error.h"
+#include "migration/migration.h"
 
 VFIOGroupList vfio_group_list =
     QLIST_HEAD_INITIALIZER(vfio_group_list);
@@ -286,6 +288,39 @@ const MemoryRegionOps vfio_region_ops = {
     },
 };
 
+/*
+ * Device state interfaces
+ */
+
+static bool vfio_devices_all_stopped_and_saving(VFIOContainer *container)
+{
+    VFIOGroup *group;
+    VFIODevice *vbasedev;
+    MigrationState *ms = migrate_get_current();
+
+    if (!migration_is_setup_or_active(ms->state)) {
+        return false;
+    }
+
+    QLIST_FOREACH(group, &container->group_list, container_next) {
+        QLIST_FOREACH(vbasedev, &group->device_list, next) {
+            VFIOMigration *migration = vbasedev->migration;
+
+            if (!migration) {
+                return false;
+            }
+
+            if ((migration->device_state & VFIO_DEVICE_STATE_SAVING) &&
+                !(migration->device_state & VFIO_DEVICE_STATE_RUNNING)) {
+                continue;
+            } else {
+                return false;
+            }
+        }
+    }
+    return true;
+}
+
 /*
  * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
  */
@@ -812,9 +847,90 @@ static void vfio_listener_region_del(MemoryListener *listener,
     }
 }
 
+static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
+                                 uint64_t size, ram_addr_t ram_addr)
+{
+    struct vfio_iommu_type1_dirty_bitmap *dbitmap;
+    struct vfio_iommu_type1_dirty_bitmap_get *range;
+    uint64_t pages;
+    int ret;
+
+    dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range));
+
+    dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range);
+    dbitmap->flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
+    range = (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data;
+    range->iova = iova;
+    range->size = size;
+
+    /*
+     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
+     * TARGET_PAGE_SIZE to mark those dirty. Hence set bitmap's pgsize to
+     * TARGET_PAGE_SIZE.
+     */
+    range->bitmap.pgsize = TARGET_PAGE_SIZE;
+
+    pages = TARGET_PAGE_ALIGN(range->size) >> TARGET_PAGE_BITS;
+    range->bitmap.size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) /
+                                         BITS_PER_BYTE;
+    range->bitmap.data = g_try_malloc0(range->bitmap.size);
+    if (!range->bitmap.data) {
+        ret = -ENOMEM;
+        goto err_out;
+    }
+
+    ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap);
+    if (ret) {
+        error_report("Failed to get dirty bitmap for iova: 0x%llx "
+                "size: 0x%llx err: %d",
+                range->iova, range->size, errno);
+        goto err_out;
+    }
+
+    cpu_physical_memory_set_dirty_lebitmap((uint64_t *)range->bitmap.data,
+                                            ram_addr, pages);
+
+    trace_vfio_get_dirty_bitmap(container->fd, range->iova, range->size,
+                                range->bitmap.size, ram_addr);
+err_out:
+    g_free(range->bitmap.data);
+    g_free(dbitmap);
+
+    return ret;
+}
+
+static int vfio_sync_dirty_bitmap(VFIOContainer *container,
+                                  MemoryRegionSection *section)
+{
+    ram_addr_t ram_addr;
+
+    ram_addr = memory_region_get_ram_addr(section->mr) +
+               section->offset_within_region;
+
+    return vfio_get_dirty_bitmap(container,
+                       TARGET_PAGE_ALIGN(section->offset_within_address_space),
+                       int128_get64(section->size), ram_addr);
+}
+
+static void vfio_listerner_log_sync(MemoryListener *listener,
+        MemoryRegionSection *section)
+{
+    VFIOContainer *container = container_of(listener, VFIOContainer, listener);
+
+    if (vfio_listener_skipped_section(section) ||
+        !container->dirty_pages_supported) {
+        return;
+    }
+
+    if (vfio_devices_all_stopped_and_saving(container)) {
+        vfio_sync_dirty_bitmap(container, section);
+    }
+}
+
 static const MemoryListener vfio_memory_listener = {
     .region_add = vfio_listener_region_add,
     .region_del = vfio_listener_region_del,
+    .log_sync = vfio_listerner_log_sync,
 };
 
 static void vfio_listener_release(VFIOContainer *container)
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index a75b5208818c..dd991bd8f265 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -163,3 +163,4 @@ 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
 vfio_load_cleanup(const char *name) " (%s)"
+vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start) "container fd=%d, iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64



  parent reply index

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-26 19:32 [PULL 00/32] VFIO updates 2020-10-26 (for QEMU 5.2 soft-freeze) Alex Williamson
2020-10-26 19:32 ` [PULL 01/32] vfio: Add function to unmap VFIO region Alex Williamson
2020-10-26 19:32 ` [PULL 02/32] vfio: Add vfio_get_object callback to VFIODeviceOps Alex Williamson
2020-10-26 19:32 ` [PULL 03/32] vfio: Add save and load functions for VFIO PCI devices Alex Williamson
2020-10-26 19:32 ` [PULL 04/32] vfio: Add migration region initialization and finalize function Alex Williamson
2020-10-26 19:33 ` [PULL 05/32] vfio: Add VM state change handler to know state of VM Alex Williamson
2020-10-26 19:33 ` [PULL 06/32] vfio: Add migration state change notifier Alex Williamson
2020-10-26 19:33 ` [PULL 07/32] vfio: Register SaveVMHandlers for VFIO device Alex Williamson
2020-10-26 19:33 ` [PULL 08/32] vfio: Add save state functions to SaveVMHandlers Alex Williamson
2020-10-26 19:33 ` [PULL 09/32] vfio: Add load " Alex Williamson
2020-10-26 19:33 ` [PULL 10/32] memory: Set DIRTY_MEMORY_MIGRATION when IOMMU is enabled Alex Williamson
2020-10-26 19:34 ` [PULL 11/32] vfio: Get migration capability flags for container Alex Williamson
2020-10-26 19:34 ` [PULL 12/32] vfio: Add function to start and stop dirty pages tracking Alex Williamson
2020-10-26 19:34 ` Alex Williamson [this message]
2020-10-26 19:34 ` [PULL 14/32] vfio: Dirty page tracking when vIOMMU is enabled Alex Williamson
2020-10-26 19:34 ` [PULL 15/32] vfio: Add ioctl to get dirty pages bitmap during dma unmap Alex Williamson
2020-10-26 19:34 ` [PULL 16/32] vfio: Make vfio-pci device migration capable Alex Williamson
2020-10-26 19:34 ` [PULL 17/32] qapi: Add VFIO devices migration stats in Migration stats Alex Williamson
2020-10-26 19:35 ` [PULL 18/32] update-linux-headers: Add vfio_zdev.h Alex Williamson
2020-10-26 19:35 ` [PULL 19/32] linux-headers: update against 5.10-rc1 Alex Williamson
2020-10-26 19:35 ` [PULL 20/32] s390x/pci: Move header files to include/hw/s390x Alex Williamson
2020-10-26 19:35 ` [PULL 21/32] vfio: Create shared routine for scanning info capabilities Alex Williamson
2020-10-26 19:35 ` [PULL 22/32] vfio: Find DMA available capability Alex Williamson
2020-10-26 19:35 ` [PULL 23/32] s390x/pci: Add routine to get the vfio dma available count Alex Williamson
2020-10-26 19:35 ` [PULL 24/32] s390x/pci: Honor DMA limits set by vfio Alex Williamson
2020-10-26 19:35 ` [PULL 25/32] s390x/pci: create a header dedicated to PCI CLP Alex Williamson
2020-10-26 19:36 ` [PULL 26/32] s390x/pci: use a PCI Group structure Alex Williamson
2020-10-26 19:36 ` [PULL 27/32] s390x/pci: clean up s390 PCI groups Alex Williamson
2020-10-26 19:36 ` [PULL 28/32] s390x/pci: use a PCI Function structure Alex Williamson
2020-10-26 19:36 ` [PULL 29/32] vfio: Add routine for finding VFIO_DEVICE_GET_INFO capabilities Alex Williamson
2020-10-26 19:36 ` [PULL 30/32] s390x/pci: get zPCI function info from host Alex Williamson
2020-10-26 19:36 ` [PULL 31/32] hw/vfio: Use lock guard macros Alex Williamson
2020-10-26 19:36 ` [PULL 32/32] vfio: fix incorrect print type Alex Williamson
2020-10-27 23:42 ` [PULL 00/32] VFIO updates 2020-10-26 (for QEMU 5.2 soft-freeze) Peter Maydell
2020-10-28  2:00   ` Alex Williamson
2020-10-28  9:18     ` Dr. David Alan Gilbert
2020-10-28 15:23       ` Miklos Szeredi
2020-10-28  9:21     ` Max Reitz
2020-10-28  8:11   ` Cornelia Huck
2020-10-28  9:28     ` Max Reitz
2020-10-28  9:41       ` Max Reitz
2020-10-28 10:12       ` Cornelia Huck
2020-10-28 15:07 ` Peter Maydell
2020-10-28 15:20   ` Matthew Rosato
2020-10-28 15:41     ` 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=160374085615.22414.9118278258571519417.stgit@gimli.home \
    --to=alex.williamson@redhat.com \
    --cc=cjia@nvidia.com \
    --cc=kwankhede@nvidia.com \
    --cc=qemu-devel@nongnu.org \
    /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
	git clone --mirror https://lore.kernel.org/qemu-devel/2 qemu-devel/git/2.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