OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

vfio: Support for RamDiscardManager in the !vIOMMU case 

Implement support for RamDiscardManager, to prepare for virtio-mem
support. Instead of mapping the whole memory section, we only map
"populated" parts and update the mapping when notified about
discarding/population of memory via the RamDiscardListener. Similarly, when
syncing the dirty bitmaps, sync only the actually mapped (populated) parts
by replaying via the notifier.

Using virtio-mem with vfio is still blocked via
ram_block_discard_disable()/ram_block_discard_require() after this patch.

Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Auger Eric <eric.auger@redhat.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: teawater <teawaterz@linux.alibaba.com>
Cc: Marek Kedzierski <mkedzier@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210413095531.25603-7-david@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
This commit is contained in:
David Hildenbrand 2021-04-13 11:55:24 +02:00 committed by Eduardo Habkost
parent 2044969f0b
commit 5e3b981c33
2 changed files with 175 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

164
hw/vfio/common.c
View File

@ -649,6 +649,110 @@ out:
rcu_read_unlock();
}
static void vfio_ram_discard_notify_discard(RamDiscardListener *rdl,
MemoryRegionSection *section)
{
VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
listener);
const hwaddr size = int128_get64(section->size);
const hwaddr iova = section->offset_within_address_space;
int ret;
/* Unmap with a single call. */
ret = vfio_dma_unmap(vrdl->container, iova, size , NULL);
if (ret) {
error_report("%s: vfio_dma_unmap() failed: %s", __func__,
strerror(-ret));
}
}
static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl,
MemoryRegionSection *section)
{
VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
listener);
const hwaddr end = section->offset_within_region +
int128_get64(section->size);
hwaddr start, next, iova;
void *vaddr;
int ret;
/*
* Map in (aligned within memory region) minimum granularity, so we can
* unmap in minimum granularity later.
*/
for (start = section->offset_within_region; start < end; start = next) {
next = ROUND_UP(start + 1, vrdl->granularity);
next = MIN(next, end);
iova = start - section->offset_within_region +
section->offset_within_address_space;
vaddr = memory_region_get_ram_ptr(section->mr) + start;
ret = vfio_dma_map(vrdl->container, iova, next - start,
vaddr, section->readonly);
if (ret) {
/* Rollback */
vfio_ram_discard_notify_discard(rdl, section);
return ret;
}
}
return 0;
}
static void vfio_register_ram_discard_listener(VFIOContainer *container,
MemoryRegionSection *section)
{
RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
VFIORamDiscardListener *vrdl;
/* Ignore some corner cases not relevant in practice. */
g_assert(QEMU_IS_ALIGNED(section->offset_within_region, TARGET_PAGE_SIZE));
g_assert(QEMU_IS_ALIGNED(section->offset_within_address_space,
TARGET_PAGE_SIZE));
g_assert(QEMU_IS_ALIGNED(int128_get64(section->size), TARGET_PAGE_SIZE));
vrdl = g_new0(VFIORamDiscardListener, 1);
vrdl->container = container;
vrdl->mr = section->mr;
vrdl->offset_within_address_space = section->offset_within_address_space;
vrdl->size = int128_get64(section->size);
vrdl->granularity = ram_discard_manager_get_min_granularity(rdm,
section->mr);
g_assert(vrdl->granularity && is_power_of_2(vrdl->granularity));
g_assert(vrdl->granularity >= 1 << ctz64(container->pgsizes));
ram_discard_listener_init(&vrdl->listener,
vfio_ram_discard_notify_populate,
vfio_ram_discard_notify_discard, true);
ram_discard_manager_register_listener(rdm, &vrdl->listener, section);
QLIST_INSERT_HEAD(&container->vrdl_list, vrdl, next);
}
static void vfio_unregister_ram_discard_listener(VFIOContainer *container,
MemoryRegionSection *section)
{
RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
VFIORamDiscardListener *vrdl = NULL;
QLIST_FOREACH(vrdl, &container->vrdl_list, next) {
if (vrdl->mr == section->mr &&
vrdl->offset_within_address_space ==
section->offset_within_address_space) {
break;
}
}
if (!vrdl) {
hw_error("vfio: Trying to unregister missing RAM discard listener");
}
ram_discard_manager_unregister_listener(rdm, &vrdl->listener);
QLIST_REMOVE(vrdl, next);
g_free(vrdl);
}
static void vfio_listener_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
@ -810,6 +914,16 @@ static void vfio_listener_region_add(MemoryListener *listener,
/* Here we assume that memory_region_is_ram(section->mr)==true */
/*
* For RAM memory regions with a RamDiscardManager, we only want to map the
* actually populated parts - and update the mapping whenever we're notified
* about changes.
*/
if (memory_region_has_ram_discard_manager(section->mr)) {
vfio_register_ram_discard_listener(container, section);
return;
}
vaddr = memory_region_get_ram_ptr(section->mr) +
section->offset_within_region +
(iova - section->offset_within_address_space);
@ -947,6 +1061,10 @@ static void vfio_listener_region_del(MemoryListener *listener,
pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1;
try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask));
} else if (memory_region_has_ram_discard_manager(section->mr)) {
vfio_unregister_ram_discard_listener(container, section);
/* Unregistering will trigger an unmap. */
try_unmap = false;
}
if (try_unmap) {
@ -1108,6 +1226,49 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
rcu_read_unlock();
}
static int vfio_ram_discard_get_dirty_bitmap(MemoryRegionSection *section,
void *opaque)
{
const hwaddr size = int128_get64(section->size);
const hwaddr iova = section->offset_within_address_space;
const ram_addr_t ram_addr = memory_region_get_ram_addr(section->mr) +
section->offset_within_region;
VFIORamDiscardListener *vrdl = opaque;
/*
* Sync the whole mapped region (spanning multiple individual mappings)
* in one go.
*/
return vfio_get_dirty_bitmap(vrdl->container, iova, size, ram_addr);
}
static int vfio_sync_ram_discard_listener_dirty_bitmap(VFIOContainer *container,
MemoryRegionSection *section)
{
RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
VFIORamDiscardListener *vrdl = NULL;
QLIST_FOREACH(vrdl, &container->vrdl_list, next) {
if (vrdl->mr == section->mr &&
vrdl->offset_within_address_space ==
section->offset_within_address_space) {
break;
}
}
if (!vrdl) {
hw_error("vfio: Trying to sync missing RAM discard listener");
}
/*
* We only want/can synchronize the bitmap for actually mapped parts -
* which correspond to populated parts. Replay all populated parts.
*/
return ram_discard_manager_replay_populated(rdm, section,
vfio_ram_discard_get_dirty_bitmap,
&vrdl);
}
static int vfio_sync_dirty_bitmap(VFIOContainer *container,
MemoryRegionSection *section)
{
@ -1139,6 +1300,8 @@ static int vfio_sync_dirty_bitmap(VFIOContainer *container,
}
}
return 0;
} else if (memory_region_has_ram_discard_manager(section->mr)) {
return vfio_sync_ram_discard_listener_dirty_bitmap(container, section);
}
ram_addr = memory_region_get_ram_addr(section->mr) +
@ -1770,6 +1933,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
container->dirty_pages_supported = false;
QLIST_INIT(&container->giommu_list);
QLIST_INIT(&container->hostwin_list);
QLIST_INIT(&container->vrdl_list);
ret = vfio_init_container(container, group->fd, errp);
if (ret) {

11
include/hw/vfio/vfio-common.h
View File

@ -91,6 +91,7 @@ typedef struct VFIOContainer {
QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
QLIST_HEAD(, VFIOGroup) group_list;
QLIST_HEAD(, VFIORamDiscardListener) vrdl_list;
QLIST_ENTRY(VFIOContainer) next;
} VFIOContainer;
@ -102,6 +103,16 @@ typedef struct VFIOGuestIOMMU {
QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
} VFIOGuestIOMMU;
typedef struct VFIORamDiscardListener {
VFIOContainer *container;
MemoryRegion *mr;
hwaddr offset_within_address_space;
hwaddr size;
uint64_t granularity;
RamDiscardListener listener;
QLIST_ENTRY(VFIORamDiscardListener) next;
} VFIORamDiscardListener;
typedef struct VFIOHostDMAWindow {
hwaddr min_iova;
hwaddr max_iova;