[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v3 05/10] vfio: Support for RamDiscardMgr in the !vIOMMU case
From: |
Alex Williamson |
Subject: |
Re: [PATCH v3 05/10] vfio: Support for RamDiscardMgr in the !vIOMMU case |
Date: |
Thu, 17 Dec 2020 11:36:12 -0700 |
On Wed, 16 Dec 2020 15:11:55 +0100
David Hildenbrand <david@redhat.com> wrote:
> Implement support for RamDiscardMgr, 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.
>
> Small mapping granularity is problematic for vfio, because we might run out
> of mappings. Indicate virito-mem as one of the problematic parts when
> warning in vfio_container_dma_reserve() to at least make users aware that
> there is such a limitation.
>
> Using virtio-mem with vfio is still blocked via
> ram_block_discard_disable()/ram_block_discard_require() after this patch.
>
> 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>
> ---
> hw/vfio/common.c | 213 +++++++++++++++++++++++++++++++++-
> include/hw/vfio/vfio-common.h | 13 +++
> 2 files changed, 225 insertions(+), 1 deletion(-)
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index 5ad88d476f..b1582be1e8 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -296,7 +296,8 @@ static void vfio_container_dma_reserve(VFIOContainer
> *container,
> container->dma_reserved += dma_mappings;
> if (!warned && container->dma_max &&
> container->dma_reserved > container->dma_max) {
> - warn_report("%s: possibly running out of DMA mappings. "
> + warn_report("%s: possibly running out of DMA mappings. E.g., try"
> + " increasing the 'block-size' of virtio-mem devies."
> " Maximum number of DMA mappings: %d", __func__,
> container->dma_max);
> }
> @@ -674,6 +675,146 @@ out:
> rcu_read_unlock();
> }
>
> +static void vfio_ram_discard_notify_discard(RamDiscardListener *rdl,
> + const MemoryRegion *mr,
> + ram_addr_t offset, ram_addr_t
> size)
> +{
> + VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
> + listener);
> + const hwaddr mr_start = MAX(offset, vrdl->offset_within_region);
> + const hwaddr mr_end = MIN(offset + size,
> + vrdl->offset_within_region + vrdl->size);
> + const hwaddr iova = mr_start - vrdl->offset_within_region +
> + vrdl->offset_within_address_space;
> + int ret;
> +
> + if (mr_start >= mr_end) {
> + return;
> + }
> +
> + /* Unmap with a single call. */
> + ret = vfio_dma_unmap(vrdl->container, iova, mr_end - mr_start, NULL);
> + if (ret) {
> + error_report("%s: vfio_dma_unmap() failed: %s", __func__,
> + strerror(-ret));
> + }
> +}
> +
> +static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl,
> + const MemoryRegion *mr,
> + ram_addr_t offset, ram_addr_t
> size)
> +{
> + VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
> + listener);
> + const hwaddr mr_end = MIN(offset + size,
> + vrdl->offset_within_region + vrdl->size);
> + hwaddr mr_start = MAX(offset, vrdl->offset_within_region);
> + hwaddr mr_next, iova;
> + void *vaddr;
> + int ret;
> +
> + /*
> + * Map in (aligned within memory region) minimum granularity, so we can
> + * unmap in minimum granularity later.
> + */
> + for (; mr_start < mr_end; mr_start = mr_next) {
> + mr_next = QEMU_ALIGN_UP(mr_start + 1, vrdl->granularity);
> + mr_next = MIN(mr_next, mr_end);
> +
> + iova = mr_start - vrdl->offset_within_region +
> + vrdl->offset_within_address_space;
> + vaddr = memory_region_get_ram_ptr(vrdl->mr) + mr_start;
> +
> + ret = vfio_dma_map(vrdl->container, iova, mr_next - mr_start,
> + vaddr, mr->readonly);
> + if (ret) {
> + /* Rollback */
> + vfio_ram_discard_notify_discard(rdl, mr, offset, size);
> + return ret;
> + }
> + }
> + return 0;
> +}
> +
> +static void vfio_ram_discard_notify_discard_all(RamDiscardListener *rdl,
> + const MemoryRegion *mr)
> +{
> + VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
> + listener);
> + int ret;
> +
> + /* Unmap with a single call. */
> + ret = vfio_dma_unmap(vrdl->container, vrdl->offset_within_address_space,
> + vrdl->size, NULL);
> + if (ret) {
> + error_report("%s: vfio_dma_unmap() failed: %s", __func__,
> + strerror(-ret));
> + }
> +}
> +
> +static void vfio_register_ram_discard_notifier(VFIOContainer *container,
> + MemoryRegionSection *section)
> +{
> + RamDiscardMgr *rdm = memory_region_get_ram_discard_mgr(section->mr);
> + RamDiscardMgrClass *rdmc = RAM_DISCARD_MGR_GET_CLASS(rdm);
> + VFIORamDiscardListener *vrdl;
> +
> + vrdl = g_new0(VFIORamDiscardListener, 1);
> + vrdl->container = container;
> + vrdl->mr = section->mr;
> + vrdl->offset_within_region = section->offset_within_region;
> + vrdl->offset_within_address_space = section->offset_within_address_space;
> + vrdl->size = int128_get64(section->size);
> + vrdl->granularity = rdmc->get_min_granularity(rdm, section->mr);
> + vrdl->dma_max = vrdl->size / vrdl->granularity;
> + if (!QEMU_IS_ALIGNED(vrdl->size, vrdl->granularity) ||
> + !QEMU_IS_ALIGNED(vrdl->offset_within_region, vrdl->granularity)) {
> + vrdl->dma_max++;
> + }
> +
> + /* Ignore some corner cases not relevant in practice. */
> + g_assert(QEMU_IS_ALIGNED(vrdl->offset_within_region, TARGET_PAGE_SIZE));
> + g_assert(QEMU_IS_ALIGNED(vrdl->offset_within_address_space,
> + TARGET_PAGE_SIZE));
> + g_assert(QEMU_IS_ALIGNED(vrdl->size, TARGET_PAGE_SIZE));
> +
> + /* We could consume quite some mappings later. */
> + vfio_container_dma_reserve(container, vrdl->dma_max);
Aha, I guess this is where the "reservation" aspect begins to appear.
Should this be its own counter though, perhaps
dma_discard_max_mappings? The populate and discard callbacks could
further divide this into used and outstanding counters. However, TBH
I'm not sure I understand the counters since this is probably the most
robust mapping path where we can actually safely nak a populate
callback. Maybe rather than any of these runtime counters we should
just walk the vrdl_list, calculate max mappings, and if that exceeds
some large fraction of available mappings, issue a warning (not that
they wouldn't be useful for tracing). Thanks,
Alex
> +
> + ram_discard_listener_init(&vrdl->listener,
> + vfio_ram_discard_notify_populate,
> + vfio_ram_discard_notify_discard,
> + vfio_ram_discard_notify_discard_all);
> + rdmc->register_listener(rdm, section->mr, &vrdl->listener);
> + QLIST_INSERT_HEAD(&container->vrdl_list, vrdl, next);
> +}
> +
> +static void vfio_unregister_ram_discard_listener(VFIOContainer *container,
> + MemoryRegionSection
> *section)
> +{
> + RamDiscardMgr *rdm = memory_region_get_ram_discard_mgr(section->mr);
> + RamDiscardMgrClass *rdmc = RAM_DISCARD_MGR_GET_CLASS(rdm);
> + VFIORamDiscardListener *vrdl = NULL;
> +
> + QLIST_FOREACH(vrdl, &container->vrdl_list, next) {
> + if (vrdl->mr == section->mr &&
> + vrdl->offset_within_region == section->offset_within_region) {
> + break;
> + }
> + }
> +
> + if (!vrdl) {
> + hw_error("vfio: Trying to unregister missing RAM discard listener");
> + }
> +
> + rdmc->unregister_listener(rdm, section->mr, &vrdl->listener);
> + QLIST_REMOVE(vrdl, next);
> +
> + vfio_container_dma_unreserve(container, vrdl->dma_max);
> +
> + g_free(vrdl);
> +}
> +
> static void vfio_listener_region_add(MemoryListener *listener,
> MemoryRegionSection *section)
> {
> @@ -834,6 +975,16 @@ 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 RamDiscardMgr, we only want to
> + * register the actually "used" parts - and update the mapping whenever
> + * we're notified about changes.
> + */
> + if (memory_region_has_ram_discard_mgr(section->mr)) {
> + vfio_register_ram_discard_notifier(container, section);
> + return;
> + }
> +
> vaddr = memory_region_get_ram_ptr(section->mr) +
> section->offset_within_region +
> (iova - section->offset_within_address_space);
> @@ -975,6 +1126,10 @@ 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_mgr(section->mr)) {
> + vfio_unregister_ram_discard_listener(container, section);
> + /* Unregistering will trigger an unmap. */
> + try_unmap = false;
> }
>
> if (try_unmap) {
> @@ -1107,6 +1262,59 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier
> *n, IOMMUTLBEntry *iotlb)
> rcu_read_unlock();
> }
>
> +static int vfio_ram_discard_notify_dirty_bitmap(RamDiscardListener *rdl,
> + const MemoryRegion *mr,
> + ram_addr_t offset,
> + ram_addr_t size)
> +{
> + VFIORamDiscardListener *vrdl = container_of(rdl, VFIORamDiscardListener,
> + listener);
> + const hwaddr mr_start = MAX(offset, vrdl->offset_within_region);
> + const hwaddr mr_end = MIN(offset + size,
> + vrdl->offset_within_region + vrdl->size);
> + const hwaddr iova = mr_start - vrdl->offset_within_region +
> + vrdl->offset_within_address_space;
> + ram_addr_t ram_addr;
> + int ret;
> +
> + if (mr_start >= mr_end) {
> + return 0;
> + }
> +
> + /*
> + * Sync the whole mapped region (spanning multiple individual mappings)
> + * in one go.
> + */
> + ram_addr = memory_region_get_ram_addr(vrdl->mr) + mr_start;
> + ret = vfio_get_dirty_bitmap(vrdl->container, iova, mr_end - mr_start,
> + ram_addr);
> + return ret;
> +}
> +
> +static int vfio_sync_ram_discard_listener_dirty_bitmap(VFIOContainer
> *container,
> + MemoryRegionSection
> *section)
> +{
> + RamDiscardMgr *rdm = memory_region_get_ram_discard_mgr(section->mr);
> + RamDiscardMgrClass *rdmc = RAM_DISCARD_MGR_GET_CLASS(rdm);
> + VFIORamDiscardListener tmp_vrdl, *vrdl = NULL;
> +
> + QLIST_FOREACH(vrdl, &container->vrdl_list, next) {
> + if (vrdl->mr == section->mr &&
> + vrdl->offset_within_region == section->offset_within_region) {
> + break;
> + }
> + }
> +
> + if (!vrdl) {
> + hw_error("vfio: Trying to sync missing RAM discard listener");
> + }
> +
> + tmp_vrdl = *vrdl;
> + ram_discard_listener_init(&tmp_vrdl.listener,
> + vfio_ram_discard_notify_dirty_bitmap, NULL,
> NULL);
> + return rdmc->replay_populated(rdm, section->mr, &tmp_vrdl.listener);
> +}
> +
> static int vfio_sync_dirty_bitmap(VFIOContainer *container,
> MemoryRegionSection *section)
> {
> @@ -1138,6 +1346,8 @@ static int vfio_sync_dirty_bitmap(VFIOContainer
> *container,
> }
> }
> return 0;
> + } else if (memory_region_has_ram_discard_mgr(section->mr)) {
> + return vfio_sync_ram_discard_listener_dirty_bitmap(container,
> section);
> }
>
> ram_addr = memory_region_get_ram_addr(section->mr) +
> @@ -1768,6 +1978,7 @@ static int vfio_connect_container(VFIOGroup *group,
> AddressSpace *as,
> container->dma_max = 0;
> 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) {
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index fed0e85f66..fba5a14c8b 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -93,6 +93,7 @@ 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;
>
> @@ -104,6 +105,18 @@ typedef struct VFIOGuestIOMMU {
> QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
> } VFIOGuestIOMMU;
>
> +typedef struct VFIORamDiscardListener {
> + VFIOContainer *container;
> + MemoryRegion *mr;
> + hwaddr offset_within_region;
> + hwaddr offset_within_address_space;
> + hwaddr size;
> + uint64_t granularity;
> + unsigned long dma_max;
> + RamDiscardListener listener;
> + QLIST_ENTRY(VFIORamDiscardListener) next;
> +} VFIORamDiscardListener;
> +
> typedef struct VFIOHostDMAWindow {
> hwaddr min_iova;
> hwaddr max_iova;
[PATCH v3 06/10] vfio: Support for RamDiscardMgr in the vIOMMU case, David Hildenbrand, 2020/12/16
[PATCH v3 07/10] softmmu/physmem: Don't use atomic operations in ram_block_discard_(disable|require), David Hildenbrand, 2020/12/16
[PATCH v3 08/10] softmmu/physmem: Extend ram_block_discard_(require|disable) by two discard types, David Hildenbrand, 2020/12/16
[PATCH v3 09/10] virtio-mem: Require only coordinated discards, David Hildenbrand, 2020/12/16
[PATCH v3 10/10] vfio: Disable only uncoordinated discards, David Hildenbrand, 2020/12/16