qemu-devel.nongnu.org archive mirror
 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 14/17] vfio: Dirty page tracking when vIOMMU is enabled
Date: Thu, 22 Oct 2020 16:42:04 +0530	[thread overview]
Message-ID: <1603365127-14202-15-git-send-email-kwankhede@nvidia.com> (raw)
In-Reply-To: <1603365127-14202-1-git-send-email-kwankhede@nvidia.com>

When vIOMMU is enabled, register MAP notifier from log_sync when all
devices in container are in stop and copy phase of migration. Call replay
and get dirty pages from notifier callback.

Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
---
 hw/vfio/common.c              | 95 ++++++++++++++++++++++++++++++++++++++++---
 hw/vfio/trace-events          |  1 +
 include/hw/vfio/vfio-common.h |  1 +
 3 files changed, 91 insertions(+), 6 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 2634387df948..98c2b1f9b190 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -442,8 +442,8 @@ static bool vfio_listener_skipped_section(MemoryRegionSection *section)
 }
 
 /* Called with rcu_read_lock held.  */
-static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr,
-                           bool *read_only)
+static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
+                               ram_addr_t *ram_addr, bool *read_only)
 {
     MemoryRegion *mr;
     hwaddr xlat;
@@ -474,8 +474,17 @@ static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr,
         return false;
     }
 
-    *vaddr = memory_region_get_ram_ptr(mr) + xlat;
-    *read_only = !writable || mr->readonly;
+    if (vaddr) {
+        *vaddr = memory_region_get_ram_ptr(mr) + xlat;
+    }
+
+    if (ram_addr) {
+        *ram_addr = memory_region_get_ram_addr(mr) + xlat;
+    }
+
+    if (read_only) {
+        *read_only = !writable || mr->readonly;
+    }
 
     return true;
 }
@@ -485,7 +494,6 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
     VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
     VFIOContainer *container = giommu->container;
     hwaddr iova = iotlb->iova + giommu->iommu_offset;
-    bool read_only;
     void *vaddr;
     int ret;
 
@@ -501,7 +509,9 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
     rcu_read_lock();
 
     if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
-        if (!vfio_get_vaddr(iotlb, &vaddr, &read_only)) {
+        bool read_only;
+
+        if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only)) {
             goto out;
         }
         /*
@@ -899,11 +909,84 @@ err_out:
     return ret;
 }
 
+static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, dirty_notify);
+    VFIOContainer *container = giommu->container;
+    hwaddr iova = iotlb->iova + giommu->iommu_offset;
+    ram_addr_t translated_addr;
+
+    trace_vfio_iommu_map_dirty_notify(iova, iova + iotlb->addr_mask);
+
+    if (iotlb->target_as != &address_space_memory) {
+        error_report("Wrong target AS \"%s\", only system memory is allowed",
+                     iotlb->target_as->name ? iotlb->target_as->name : "none");
+        return;
+    }
+
+    rcu_read_lock();
+
+    if (vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL)) {
+        int ret;
+
+        ret = vfio_get_dirty_bitmap(container, iova, iotlb->addr_mask + 1,
+                                    translated_addr);
+        if (ret) {
+            error_report("vfio_iommu_map_dirty_notify(%p, 0x%"HWADDR_PRIx", "
+                         "0x%"HWADDR_PRIx") = %d (%m)",
+                         container, iova,
+                         iotlb->addr_mask + 1, ret);
+        }
+    }
+
+    rcu_read_unlock();
+}
+
 static int vfio_sync_dirty_bitmap(VFIOContainer *container,
                                   MemoryRegionSection *section)
 {
     ram_addr_t ram_addr;
 
+    if (memory_region_is_iommu(section->mr)) {
+        VFIOGuestIOMMU *giommu;
+        int ret = 0;
+
+        QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) {
+            if (MEMORY_REGION(giommu->iommu) == section->mr &&
+                giommu->n.start == section->offset_within_region) {
+                Int128 llend;
+                Error *err = NULL;
+                int idx = memory_region_iommu_attrs_to_index(giommu->iommu,
+                                                       MEMTXATTRS_UNSPECIFIED);
+
+                llend = int128_add(int128_make64(section->offset_within_region),
+                                   section->size);
+                llend = int128_sub(llend, int128_one());
+
+                iommu_notifier_init(&giommu->dirty_notify,
+                                    vfio_iommu_map_dirty_notify,
+                                    IOMMU_NOTIFIER_MAP,
+                                    section->offset_within_region,
+                                    int128_get64(llend),
+                                    idx);
+                ret = memory_region_register_iommu_notifier(section->mr,
+                                                  &giommu->dirty_notify, &err);
+                if (ret) {
+                    error_report_err(err);
+                    break;
+                }
+
+                memory_region_iommu_replay(giommu->iommu,
+                                           &giommu->dirty_notify);
+
+                memory_region_unregister_iommu_notifier(section->mr,
+                                                        &giommu->dirty_notify);
+                break;
+            }
+        }
+        return ret;
+    }
+
     ram_addr = memory_region_get_ram_addr(section->mr) +
                section->offset_within_region;
 
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index c3b35aa2cce8..d9cb8998a228 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_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
+vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index b1c1b18fd228..92872fae59ee 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -99,6 +99,7 @@ typedef struct VFIOGuestIOMMU {
     IOMMUMemoryRegion *iommu;
     hwaddr iommu_offset;
     IOMMUNotifier n;
+    IOMMUNotifier dirty_notify;
     QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
 } VFIOGuestIOMMU;
 
-- 
2.7.0



  parent reply	other threads:[~2020-10-22 12:20 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 ` [PATCH v27 09/17] vfio: Add load " Kirti Wankhede
2020-10-22 19:50   ` 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 ` Kirti Wankhede [this message]
2020-10-22 20:37   ` [PATCH v27 14/17] vfio: Dirty page tracking when vIOMMU is enabled 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=1603365127-14202-15-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).