diff options
author | Stefan Hajnoczi <stefanha@redhat.com> | 2023-10-16 12:34:17 -0400 |
---|---|---|
committer | Stefan Hajnoczi <stefanha@redhat.com> | 2023-10-16 12:34:17 -0400 |
commit | bc2b89b38582b1cc7198428c9174fbbbf31245ad (patch) | |
tree | d15cdfa911a8b6d6eecec0d0ecaa1d1eed346075 | |
parent | 63011373ad22c794a013da69663c03f1297a5c56 (diff) | |
parent | ee6398d862c108f8136a26d93d26680f3d222a3a (diff) | |
download | qemu-bc2b89b38582b1cc7198428c9174fbbbf31245ad.zip qemu-bc2b89b38582b1cc7198428c9174fbbbf31245ad.tar.gz qemu-bc2b89b38582b1cc7198428c9174fbbbf31245ad.tar.bz2 |
Merge tag 'mem-2023-10-12' of https://github.com/davidhildenbrand/qemu into staging
Hi,
"Host Memory Backends" and "Memory devices" queue ("mem"):
- Support memory devices with multiple memslots
- Support memory devices that dynamically consume memslots
- Support memory devices that can automatically decide on the number of
memslots to use
- virtio-mem support for exposing memory dynamically via multiple
memslots
- Some required cleanups/refactorings
# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEEG9nKrXNcTDpGDfzKTd4Q9wD/g1oFAmUn+XMRHGRhdmlkQHJl
# ZGhhdC5jb20ACgkQTd4Q9wD/g1qDHA//T01suTa+uzrcoJHoMWN11S47WnAmbuTo
# vVakucLBPMJAa9xZeCy3OavXaVGpHkw+t6g3OFknof0LfQ5/j9iE3Q1PxURN7g5j
# SJ2WJXCoceM6T4TMhPvVvgEaYjFmESqZB5FZgedMT0QRyhAxMuF9pCkWhk1O3OAV
# JqQKqLFiGcv60AEuBYGZGzgiOUv8EJ5gKwRF4VOdyHIxqZDw1aZXzlcd4TzFZBQ7
# rwW/3ef+sFmUJdmfrSrqcIlQSRrqZ2w95xATDzLTIEEUT3SWqh/E95EZWIz1M0oQ
# NgWgFiLCR1KOj7bWFhLXT7IfyLh0mEysD+P/hY6QwQ4RewWG7EW5UK+JFswssdcZ
# rEj5XpHZzev/wx7hM4bWsoQ+VIvrH7j3uYGyWkcgYRbdDEkWDv2rsT23lwGYNhht
# oBsrdEBELRw6v4C8doq/+sCmHmuxUMqTGwbArCQVnB1XnLxOEkuqlnfq5MORkzNF
# fxbIRx+LRluOllC0HVaDQd8qxRq1+UC5WIpAcDcrouy4HGgi1onWKrXpgjIAbVyH
# M6cENkK7rnRk96gpeXdmrf0h9HqRciAOY8oUsFsvLyKBOCPBWDrLyOQEY5UoSdtD
# m4QpEVgywCy2z1uU/UObeT/UxJy/9EL/Zb+DHoEK06iEhwONoUJjEBYMJD38RMkk
# mwPTB4UAk9g=
# =s69t
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 12 Oct 2023 09:49:39 EDT
# gpg: using RSA key 1BD9CAAD735C4C3A460DFCCA4DDE10F700FF835A
# gpg: issuer "david@redhat.com"
# gpg: Good signature from "David Hildenbrand <david@redhat.com>" [unknown]
# gpg: aka "David Hildenbrand <davidhildenbrand@gmail.com>" [full]
# gpg: aka "David Hildenbrand <hildenbr@in.tum.de>" [unknown]
# gpg: WARNING: The key's User ID is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 1BD9 CAAD 735C 4C3A 460D FCCA 4DDE 10F7 00FF 835A
* tag 'mem-2023-10-12' of https://github.com/davidhildenbrand/qemu:
virtio-mem: Mark memslot alias memory regions unmergeable
memory,vhost: Allow for marking memory device memory regions unmergeable
virtio-mem: Expose device memory dynamically via multiple memslots if enabled
virtio-mem: Update state to match bitmap as soon as it's been migrated
virtio-mem: Pass non-const VirtIOMEM via virtio_mem_range_cb
memory: Clarify mapping requirements for RamDiscardManager
memory-device,vhost: Support automatic decision on the number of memslots
vhost: Add vhost_get_max_memslots()
kvm: Add stub for kvm_get_max_memslots()
memory-device,vhost: Support memory devices that dynamically consume memslots
memory-device: Track required and actually used memslots in DeviceMemoryState
stubs: Rename qmp_memory_device.c to memory_device.c
memory-device: Support memory devices with multiple memslots
vhost: Return number of free memslots
kvm: Return number of free memslots
softmmu/physmem: Fixup qemu_ram_block_from_host() documentation
vhost: Remove vhost_backend_can_merge() callback
vhost: Rework memslot filtering and fix "used_memslot" tracking
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
-rw-r--r-- | MAINTAINERS | 1 | ||||
-rw-r--r-- | accel/kvm/kvm-all.c | 35 | ||||
-rw-r--r-- | accel/stubs/kvm-stub.c | 9 | ||||
-rw-r--r-- | hw/mem/memory-device.c | 196 | ||||
-rw-r--r-- | hw/virtio/vhost-stub.c | 9 | ||||
-rw-r--r-- | hw/virtio/vhost-user.c | 21 | ||||
-rw-r--r-- | hw/virtio/vhost-vdpa.c | 1 | ||||
-rw-r--r-- | hw/virtio/vhost.c | 103 | ||||
-rw-r--r-- | hw/virtio/virtio-mem-pci.c | 21 | ||||
-rw-r--r-- | hw/virtio/virtio-mem.c | 330 | ||||
-rw-r--r-- | include/exec/cpu-common.h | 15 | ||||
-rw-r--r-- | include/exec/memory.h | 27 | ||||
-rw-r--r-- | include/hw/boards.h | 14 | ||||
-rw-r--r-- | include/hw/mem/memory-device.h | 57 | ||||
-rw-r--r-- | include/hw/virtio/vhost-backend.h | 9 | ||||
-rw-r--r-- | include/hw/virtio/vhost.h | 3 | ||||
-rw-r--r-- | include/hw/virtio/virtio-mem.h | 32 | ||||
-rw-r--r-- | include/sysemu/kvm.h | 4 | ||||
-rw-r--r-- | include/sysemu/kvm_int.h | 1 | ||||
-rw-r--r-- | stubs/memory_device.c (renamed from stubs/qmp_memory_device.c) | 10 | ||||
-rw-r--r-- | stubs/meson.build | 2 | ||||
-rw-r--r-- | system/memory.c | 35 | ||||
-rw-r--r-- | system/physmem.c | 17 |
23 files changed, 839 insertions, 113 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index ceea4c2..04e87c20 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2891,6 +2891,7 @@ F: hw/mem/pc-dimm.c F: include/hw/mem/memory-device.h F: include/hw/mem/nvdimm.h F: include/hw/mem/pc-dimm.h +F: stubs/memory_device.c F: docs/nvdimm.txt SPICE diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 72e1d11..3f7eafe 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -174,13 +174,31 @@ void kvm_resample_fd_notify(int gsi) } } -int kvm_get_max_memslots(void) +unsigned int kvm_get_max_memslots(void) { KVMState *s = KVM_STATE(current_accel()); return s->nr_slots; } +unsigned int kvm_get_free_memslots(void) +{ + unsigned int used_slots = 0; + KVMState *s = kvm_state; + int i; + + kvm_slots_lock(); + for (i = 0; i < s->nr_as; i++) { + if (!s->as[i].ml) { + continue; + } + used_slots = MAX(used_slots, s->as[i].ml->nr_used_slots); + } + kvm_slots_unlock(); + + return s->nr_slots - used_slots; +} + /* Called with KVMMemoryListener.slots_lock held */ static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml) { @@ -196,19 +214,6 @@ static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml) return NULL; } -bool kvm_has_free_slot(MachineState *ms) -{ - KVMState *s = KVM_STATE(ms->accelerator); - bool result; - KVMMemoryListener *kml = &s->memory_listener; - - kvm_slots_lock(); - result = !!kvm_get_free_slot(kml); - kvm_slots_unlock(); - - return result; -} - /* Called with KVMMemoryListener.slots_lock held */ static KVMSlot *kvm_alloc_slot(KVMMemoryListener *kml) { @@ -1387,6 +1392,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, } start_addr += slot_size; size -= slot_size; + kml->nr_used_slots--; } while (size); return; } @@ -1412,6 +1418,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, ram_start_offset += slot_size; ram += slot_size; size -= slot_size; + kml->nr_used_slots++; } while (size); } diff --git a/accel/stubs/kvm-stub.c b/accel/stubs/kvm-stub.c index 235dc66..51f522e 100644 --- a/accel/stubs/kvm-stub.c +++ b/accel/stubs/kvm-stub.c @@ -109,9 +109,14 @@ int kvm_irqchip_remove_irqfd_notifier_gsi(KVMState *s, EventNotifier *n, return -ENOSYS; } -bool kvm_has_free_slot(MachineState *ms) +unsigned int kvm_get_max_memslots(void) { - return false; + return 0; +} + +unsigned int kvm_get_free_memslots(void) +{ + return 0; } void kvm_init_cpu_signals(CPUState *cpu) diff --git a/hw/mem/memory-device.c b/hw/mem/memory-device.c index 667d56b..ae38f48 100644 --- a/hw/mem/memory-device.c +++ b/hw/mem/memory-device.c @@ -52,19 +52,135 @@ static int memory_device_build_list(Object *obj, void *opaque) return 0; } -static void memory_device_check_addable(MachineState *ms, MemoryRegion *mr, - Error **errp) +static unsigned int memory_device_get_memslots(MemoryDeviceState *md) { + const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); + + if (mdc->get_memslots) { + return mdc->get_memslots(md); + } + return 1; +} + +/* + * Memslots that are reserved by memory devices (required but still reported + * as free from KVM / vhost). + */ +static unsigned int get_reserved_memslots(MachineState *ms) +{ + if (ms->device_memory->used_memslots > + ms->device_memory->required_memslots) { + /* This is unexpected, and we warned already in the memory notifier. */ + return 0; + } + return ms->device_memory->required_memslots - + ms->device_memory->used_memslots; +} + +unsigned int memory_devices_get_reserved_memslots(void) +{ + if (!current_machine->device_memory) { + return 0; + } + return get_reserved_memslots(current_machine); +} + +bool memory_devices_memslot_auto_decision_active(void) +{ + if (!current_machine->device_memory) { + return false; + } + + return current_machine->device_memory->memslot_auto_decision_active; +} + +static unsigned int memory_device_memslot_decision_limit(MachineState *ms, + MemoryRegion *mr) +{ + const unsigned int reserved = get_reserved_memslots(ms); + const uint64_t size = memory_region_size(mr); + unsigned int max = vhost_get_max_memslots(); + unsigned int free = vhost_get_free_memslots(); + uint64_t available_space; + unsigned int memslots; + + if (kvm_enabled()) { + max = MIN(max, kvm_get_max_memslots()); + free = MIN(free, kvm_get_free_memslots()); + } + + /* + * If we only have less overall memslots than what we consider reasonable, + * just keep it to a minimum. + */ + if (max < MEMORY_DEVICES_SAFE_MAX_MEMSLOTS) { + return 1; + } + + /* + * Consider our soft-limit across all memory devices. We don't really + * expect to exceed this limit in reasonable configurations. + */ + if (MEMORY_DEVICES_SOFT_MEMSLOT_LIMIT <= + ms->device_memory->required_memslots) { + return 1; + } + memslots = MEMORY_DEVICES_SOFT_MEMSLOT_LIMIT - + ms->device_memory->required_memslots; + + /* + * Consider the actually still free memslots. This is only relevant if + * other memslot consumers would consume *significantly* more memslots than + * what we prepared for (> 253). Unlikely, but let's just handle it + * cleanly. + */ + memslots = MIN(memslots, free - reserved); + if (memslots < 1 || unlikely(free < reserved)) { + return 1; + } + + /* We cannot have any other memory devices? So give all to this device. */ + if (size == ms->maxram_size - ms->ram_size) { + return memslots; + } + + /* + * Simple heuristic: equally distribute the memslots over the space + * still available for memory devices. + */ + available_space = ms->maxram_size - ms->ram_size - + ms->device_memory->used_region_size; + memslots = (double)memslots * size / available_space; + return memslots < 1 ? 1 : memslots; +} + +static void memory_device_check_addable(MachineState *ms, MemoryDeviceState *md, + MemoryRegion *mr, Error **errp) +{ + const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); const uint64_t used_region_size = ms->device_memory->used_region_size; const uint64_t size = memory_region_size(mr); + const unsigned int reserved_memslots = get_reserved_memslots(ms); + unsigned int required_memslots, memslot_limit; + + /* + * Instruct the device to decide how many memslots to use, if applicable, + * before we query the number of required memslots the first time. + */ + if (mdc->decide_memslots) { + memslot_limit = memory_device_memslot_decision_limit(ms, mr); + mdc->decide_memslots(md, memslot_limit); + } + required_memslots = memory_device_get_memslots(md); - /* we will need a new memory slot for kvm and vhost */ - if (kvm_enabled() && !kvm_has_free_slot(ms)) { - error_setg(errp, "hypervisor has no free memory slots left"); + /* we will need memory slots for kvm and vhost */ + if (kvm_enabled() && + kvm_get_free_memslots() < required_memslots + reserved_memslots) { + error_setg(errp, "hypervisor has not enough free memory slots left"); return; } - if (!vhost_has_free_slot()) { - error_setg(errp, "a used vhost backend has no free memory slots left"); + if (vhost_get_free_memslots() < required_memslots + reserved_memslots) { + error_setg(errp, "a used vhost backend has not enough free memory slots left"); return; } @@ -233,7 +349,7 @@ void memory_device_pre_plug(MemoryDeviceState *md, MachineState *ms, goto out; } - memory_device_check_addable(ms, mr, &local_err); + memory_device_check_addable(ms, md, mr, &local_err); if (local_err) { goto out; } @@ -264,6 +380,7 @@ out: void memory_device_plug(MemoryDeviceState *md, MachineState *ms) { const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); + const unsigned int memslots = memory_device_get_memslots(md); const uint64_t addr = mdc->get_addr(md); MemoryRegion *mr; @@ -275,6 +392,11 @@ void memory_device_plug(MemoryDeviceState *md, MachineState *ms) g_assert(ms->device_memory); ms->device_memory->used_region_size += memory_region_size(mr); + ms->device_memory->required_memslots += memslots; + if (mdc->decide_memslots && memslots > 1) { + ms->device_memory->memslot_auto_decision_active++; + } + memory_region_add_subregion(&ms->device_memory->mr, addr - ms->device_memory->base, mr); trace_memory_device_plug(DEVICE(md)->id ? DEVICE(md)->id : "", addr); @@ -283,6 +405,7 @@ void memory_device_plug(MemoryDeviceState *md, MachineState *ms) void memory_device_unplug(MemoryDeviceState *md, MachineState *ms) { const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); + const unsigned int memslots = memory_device_get_memslots(md); MemoryRegion *mr; /* @@ -293,7 +416,12 @@ void memory_device_unplug(MemoryDeviceState *md, MachineState *ms) g_assert(ms->device_memory); memory_region_del_subregion(&ms->device_memory->mr, mr); + + if (mdc->decide_memslots && memslots > 1) { + ms->device_memory->memslot_auto_decision_active--; + } ms->device_memory->used_region_size -= memory_region_size(mr); + ms->device_memory->required_memslots -= memslots; trace_memory_device_unplug(DEVICE(md)->id ? DEVICE(md)->id : "", mdc->get_addr(md)); } @@ -313,6 +441,50 @@ uint64_t memory_device_get_region_size(const MemoryDeviceState *md, return memory_region_size(mr); } +static void memory_devices_region_mod(MemoryListener *listener, + MemoryRegionSection *mrs, bool add) +{ + DeviceMemoryState *dms = container_of(listener, DeviceMemoryState, + listener); + + if (!memory_region_is_ram(mrs->mr)) { + warn_report("Unexpected memory region mapped into device memory region."); + return; + } + + /* + * The expectation is that each distinct RAM memory region section in + * our region for memory devices consumes exactly one memslot in KVM + * and in vhost. For vhost, this is true, except: + * * ROM memory regions don't consume a memslot. These get used very + * rarely for memory devices (R/O NVDIMMs). + * * Memslots without a fd (memory-backend-ram) don't necessarily + * consume a memslot. Such setups are quite rare and possibly bogus: + * the memory would be inaccessible by such vhost devices. + * + * So for vhost, in corner cases we might over-estimate the number of + * memslots that are currently used or that might still be reserved + * (required - used). + */ + dms->used_memslots += add ? 1 : -1; + + if (dms->used_memslots > dms->required_memslots) { + warn_report("Memory devices use more memory slots than indicated as required."); + } +} + +static void memory_devices_region_add(MemoryListener *listener, + MemoryRegionSection *mrs) +{ + return memory_devices_region_mod(listener, mrs, true); +} + +static void memory_devices_region_del(MemoryListener *listener, + MemoryRegionSection *mrs) +{ + return memory_devices_region_mod(listener, mrs, false); +} + void machine_memory_devices_init(MachineState *ms, hwaddr base, uint64_t size) { g_assert(size); @@ -322,8 +494,16 @@ void machine_memory_devices_init(MachineState *ms, hwaddr base, uint64_t size) memory_region_init(&ms->device_memory->mr, OBJECT(ms), "device-memory", size); + address_space_init(&ms->device_memory->as, &ms->device_memory->mr, + "device-memory"); memory_region_add_subregion(get_system_memory(), ms->device_memory->base, &ms->device_memory->mr); + + /* Track the number of memslots used by memory devices. */ + ms->device_memory->listener.region_add = memory_devices_region_add; + ms->device_memory->listener.region_del = memory_devices_region_del; + memory_listener_register(&ms->device_memory->listener, + &ms->device_memory->as); } static const TypeInfo memory_device_info = { diff --git a/hw/virtio/vhost-stub.c b/hw/virtio/vhost-stub.c index aa858ef..52d42ad 100644 --- a/hw/virtio/vhost-stub.c +++ b/hw/virtio/vhost-stub.c @@ -2,9 +2,14 @@ #include "hw/virtio/vhost.h" #include "hw/virtio/vhost-user.h" -bool vhost_has_free_slot(void) +unsigned int vhost_get_max_memslots(void) { - return true; + return UINT_MAX; +} + +unsigned int vhost_get_free_memslots(void) +{ + return UINT_MAX; } bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 3766b41..68eb1f0 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -2327,19 +2327,6 @@ static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr) return -ENOTSUP; } -static bool vhost_user_can_merge(struct vhost_dev *dev, - uint64_t start1, uint64_t size1, - uint64_t start2, uint64_t size2) -{ - ram_addr_t offset; - int mfd, rfd; - - (void)vhost_user_get_mr_data(start1, &offset, &mfd); - (void)vhost_user_get_mr_data(start2, &offset, &rfd); - - return mfd == rfd; -} - static int vhost_user_net_set_mtu(struct vhost_dev *dev, uint16_t mtu) { VhostUserMsg msg; @@ -2622,10 +2609,9 @@ vhost_user_crypto_close_session(struct vhost_dev *dev, uint64_t session_id) return 0; } -static bool vhost_user_mem_section_filter(struct vhost_dev *dev, - MemoryRegionSection *section) +static bool vhost_user_no_private_memslots(struct vhost_dev *dev) { - return memory_region_get_fd(section->mr) >= 0; + return true; } static int vhost_user_get_inflight_fd(struct vhost_dev *dev, @@ -2868,6 +2854,7 @@ const VhostOps user_ops = { .vhost_backend_init = vhost_user_backend_init, .vhost_backend_cleanup = vhost_user_backend_cleanup, .vhost_backend_memslots_limit = vhost_user_memslots_limit, + .vhost_backend_no_private_memslots = vhost_user_no_private_memslots, .vhost_set_log_base = vhost_user_set_log_base, .vhost_set_mem_table = vhost_user_set_mem_table, .vhost_set_vring_addr = vhost_user_set_vring_addr, @@ -2886,7 +2873,6 @@ const VhostOps user_ops = { .vhost_set_vring_enable = vhost_user_set_vring_enable, .vhost_requires_shm_log = vhost_user_requires_shm_log, .vhost_migration_done = vhost_user_migration_done, - .vhost_backend_can_merge = vhost_user_can_merge, .vhost_net_set_mtu = vhost_user_net_set_mtu, .vhost_set_iotlb_callback = vhost_user_set_iotlb_callback, .vhost_send_device_iotlb_msg = vhost_user_send_device_iotlb_msg, @@ -2894,7 +2880,6 @@ const VhostOps user_ops = { .vhost_set_config = vhost_user_set_config, .vhost_crypto_create_session = vhost_user_crypto_create_session, .vhost_crypto_close_session = vhost_user_crypto_close_session, - .vhost_backend_mem_section_filter = vhost_user_mem_section_filter, .vhost_get_inflight_fd = vhost_user_get_inflight_fd, .vhost_set_inflight_fd = vhost_user_set_inflight_fd, .vhost_dev_start = vhost_user_dev_start, diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 89ff02a..819b2d8 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -1512,7 +1512,6 @@ const VhostOps vdpa_ops = { .vhost_set_config = vhost_vdpa_set_config, .vhost_requires_shm_log = NULL, .vhost_migration_done = NULL, - .vhost_backend_can_merge = NULL, .vhost_net_set_mtu = NULL, .vhost_set_iotlb_callback = NULL, .vhost_send_device_iotlb_msg = NULL, diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 9cfac40..9f37206 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -23,6 +23,7 @@ #include "qemu/log.h" #include "standard-headers/linux/vhost_types.h" #include "hw/virtio/virtio-bus.h" +#include "hw/mem/memory-device.h" #include "migration/blocker.h" #include "migration/qemu-file-types.h" #include "sysemu/dma.h" @@ -45,20 +46,44 @@ static struct vhost_log *vhost_log; static struct vhost_log *vhost_log_shm; +/* Memslots used by backends that support private memslots (without an fd). */ static unsigned int used_memslots; + +/* Memslots used by backends that only support shared memslots (with an fd). */ +static unsigned int used_shared_memslots; + static QLIST_HEAD(, vhost_dev) vhost_devices = QLIST_HEAD_INITIALIZER(vhost_devices); -bool vhost_has_free_slot(void) +unsigned int vhost_get_max_memslots(void) +{ + unsigned int max = UINT_MAX; + struct vhost_dev *hdev; + + QLIST_FOREACH(hdev, &vhost_devices, entry) { + max = MIN(max, hdev->vhost_ops->vhost_backend_memslots_limit(hdev)); + } + return max; +} + +unsigned int vhost_get_free_memslots(void) { - unsigned int slots_limit = ~0U; + unsigned int free = UINT_MAX; struct vhost_dev *hdev; QLIST_FOREACH(hdev, &vhost_devices, entry) { unsigned int r = hdev->vhost_ops->vhost_backend_memslots_limit(hdev); - slots_limit = MIN(slots_limit, r); + unsigned int cur_free; + + if (hdev->vhost_ops->vhost_backend_no_private_memslots && + hdev->vhost_ops->vhost_backend_no_private_memslots(hdev)) { + cur_free = r - used_shared_memslots; + } else { + cur_free = r - used_memslots; + } + free = MIN(free, cur_free); } - return slots_limit > used_memslots; + return free; } static void vhost_dev_sync_region(struct vhost_dev *dev, @@ -474,8 +499,7 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev, * vhost_section: identify sections needed for vhost access * * We only care about RAM sections here (where virtqueue and guest - * internals accessed by virtio might live). If we find one we still - * allow the backend to potentially filter it out of our list. + * internals accessed by virtio might live). */ static bool vhost_section(struct vhost_dev *dev, MemoryRegionSection *section) { @@ -502,8 +526,16 @@ static bool vhost_section(struct vhost_dev *dev, MemoryRegionSection *section) return false; } - if (dev->vhost_ops->vhost_backend_mem_section_filter && - !dev->vhost_ops->vhost_backend_mem_section_filter(dev, section)) { + /* + * Some backends (like vhost-user) can only handle memory regions + * that have an fd (can be mapped into a different process). Filter + * the ones without an fd out, if requested. + * + * TODO: we might have to limit to MAP_SHARED as well. + */ + if (memory_region_get_fd(section->mr) < 0 && + dev->vhost_ops->vhost_backend_no_private_memslots && + dev->vhost_ops->vhost_backend_no_private_memslots(dev)) { trace_vhost_reject_section(mr->name, 2); return false; } @@ -568,7 +600,14 @@ static void vhost_commit(MemoryListener *listener) dev->n_mem_sections * sizeof dev->mem->regions[0]; dev->mem = g_realloc(dev->mem, regions_size); dev->mem->nregions = dev->n_mem_sections; - used_memslots = dev->mem->nregions; + + if (dev->vhost_ops->vhost_backend_no_private_memslots && + dev->vhost_ops->vhost_backend_no_private_memslots(dev)) { + used_shared_memslots = dev->mem->nregions; + } else { + used_memslots = dev->mem->nregions; + } + for (i = 0; i < dev->n_mem_sections; i++) { struct vhost_memory_region *cur_vmr = dev->mem->regions + i; struct MemoryRegionSection *mrs = dev->mem_sections + i; @@ -668,7 +707,7 @@ static void vhost_region_add_section(struct vhost_dev *dev, mrs_size, mrs_host); } - if (dev->n_tmp_sections) { + if (dev->n_tmp_sections && !section->unmergeable) { /* Since we already have at least one section, lets see if * this extends it; since we're scanning in order, we only * have to look at the last one, and the FlatView that calls @@ -701,11 +740,7 @@ static void vhost_region_add_section(struct vhost_dev *dev, size_t offset = mrs_gpa - prev_gpa_start; if (prev_host_start + offset == mrs_host && - section->mr == prev_sec->mr && - (!dev->vhost_ops->vhost_backend_can_merge || - dev->vhost_ops->vhost_backend_can_merge(dev, - mrs_host, mrs_size, - prev_host_start, prev_size))) { + section->mr == prev_sec->mr && !prev_sec->unmergeable) { uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size); need_add = false; prev_sec->offset_within_address_space = @@ -1400,6 +1435,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type, uint32_t busyloop_timeout, Error **errp) { + unsigned int used, reserved, limit; uint64_t features; int i, r, n_initialized_vqs = 0; @@ -1426,6 +1462,19 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, goto fail; } + limit = hdev->vhost_ops->vhost_backend_memslots_limit(hdev); + if (limit < MEMORY_DEVICES_SAFE_MAX_MEMSLOTS && + memory_devices_memslot_auto_decision_active()) { + error_setg(errp, "some memory device (like virtio-mem)" + " decided how many memory slots to use based on the overall" + " number of memory slots; this vhost backend would further" + " restricts the overall number of memory slots"); + error_append_hint(errp, "Try plugging this vhost backend before" + " plugging such memory devices.\n"); + r = -EINVAL; + goto fail; + } + for (i = 0; i < hdev->nvqs; ++i, ++n_initialized_vqs) { r = vhost_virtqueue_init(hdev, hdev->vqs + i, hdev->vq_index + i); if (r < 0) { @@ -1495,9 +1544,27 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, memory_listener_register(&hdev->memory_listener, &address_space_memory); QLIST_INSERT_HEAD(&vhost_devices, hdev, entry); - if (used_memslots > hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) { - error_setg(errp, "vhost backend memory slots limit is less" - " than current number of present memory slots"); + /* + * The listener we registered properly updated the corresponding counter. + * So we can trust that these values are accurate. + */ + if (hdev->vhost_ops->vhost_backend_no_private_memslots && + hdev->vhost_ops->vhost_backend_no_private_memslots(hdev)) { + used = used_shared_memslots; + } else { + used = used_memslots; + } + /* + * We assume that all reserved memslots actually require a real memslot + * in our vhost backend. This might not be true, for example, if the + * memslot would be ROM. If ever relevant, we can optimize for that -- + * but we'll need additional information about the reservations. + */ + reserved = memory_devices_get_reserved_memslots(); + if (used + reserved > limit) { + error_setg(errp, "vhost backend memory slots limit (%d) is less" + " than current number of used (%d) and reserved (%d)" + " memory slots for memory devices.", limit, used, reserved); r = -EINVAL; goto fail_busyloop; } diff --git a/hw/virtio/virtio-mem-pci.c b/hw/virtio/virtio-mem-pci.c index c4597e0..1b4e9a3 100644 --- a/hw/virtio/virtio-mem-pci.c +++ b/hw/virtio/virtio-mem-pci.c @@ -48,6 +48,25 @@ static MemoryRegion *virtio_mem_pci_get_memory_region(MemoryDeviceState *md, return vmc->get_memory_region(vmem, errp); } +static void virtio_mem_pci_decide_memslots(MemoryDeviceState *md, + unsigned int limit) +{ + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vmc = VIRTIO_MEM_GET_CLASS(vmem); + + vmc->decide_memslots(vmem, limit); +} + +static unsigned int virtio_mem_pci_get_memslots(MemoryDeviceState *md) +{ + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vmc = VIRTIO_MEM_GET_CLASS(vmem); + + return vmc->get_memslots(vmem); +} + static uint64_t virtio_mem_pci_get_plugged_size(const MemoryDeviceState *md, Error **errp) { @@ -150,6 +169,8 @@ static void virtio_mem_pci_class_init(ObjectClass *klass, void *data) mdc->set_addr = virtio_mem_pci_set_addr; mdc->get_plugged_size = virtio_mem_pci_get_plugged_size; mdc->get_memory_region = virtio_mem_pci_get_memory_region; + mdc->decide_memslots = virtio_mem_pci_decide_memslots; + mdc->get_memslots = virtio_mem_pci_get_memslots; mdc->fill_device_info = virtio_mem_pci_fill_device_info; mdc->get_min_alignment = virtio_mem_pci_get_min_alignment; diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index da5b09c..9dc3c61 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -67,6 +67,13 @@ static uint32_t virtio_mem_default_thp_size(void) } /* + * The minimum memslot size depends on this setting ("sane default"), the + * device block size, and the memory backend page size. The last (or single) + * memslot might be smaller than this constant. + */ +#define VIRTIO_MEM_MIN_MEMSLOT_SIZE (1 * GiB) + +/* * We want to have a reasonable default block size such that * 1. We avoid splitting THPs when unplugging memory, which degrades * performance. @@ -177,10 +184,10 @@ static bool virtio_mem_is_busy(void) return migration_in_incoming_postcopy() || !migration_is_idle(); } -typedef int (*virtio_mem_range_cb)(const VirtIOMEM *vmem, void *arg, +typedef int (*virtio_mem_range_cb)(VirtIOMEM *vmem, void *arg, uint64_t offset, uint64_t size); -static int virtio_mem_for_each_unplugged_range(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_for_each_unplugged_range(VirtIOMEM *vmem, void *arg, virtio_mem_range_cb cb) { unsigned long first_zero_bit, last_zero_bit; @@ -204,7 +211,7 @@ static int virtio_mem_for_each_unplugged_range(const VirtIOMEM *vmem, void *arg, return ret; } -static int virtio_mem_for_each_plugged_range(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_for_each_plugged_range(VirtIOMEM *vmem, void *arg, virtio_mem_range_cb cb) { unsigned long first_bit, last_bit; @@ -483,6 +490,96 @@ static bool virtio_mem_valid_range(const VirtIOMEM *vmem, uint64_t gpa, return true; } +static void virtio_mem_activate_memslot(VirtIOMEM *vmem, unsigned int idx) +{ + const uint64_t memslot_offset = idx * vmem->memslot_size; + + assert(vmem->memslots); + + /* + * Instead of enabling/disabling memslots, we add/remove them. This should + * make address space updates faster, because we don't have to loop over + * many disabled subregions. + */ + if (memory_region_is_mapped(&vmem->memslots[idx])) { + return; + } + memory_region_add_subregion(vmem->mr, memslot_offset, &vmem->memslots[idx]); +} + +static void virtio_mem_deactivate_memslot(VirtIOMEM *vmem, unsigned int idx) +{ + assert(vmem->memslots); + + if (!memory_region_is_mapped(&vmem->memslots[idx])) { + return; + } + memory_region_del_subregion(vmem->mr, &vmem->memslots[idx]); +} + +static void virtio_mem_activate_memslots_to_plug(VirtIOMEM *vmem, + uint64_t offset, uint64_t size) +{ + const unsigned int start_idx = offset / vmem->memslot_size; + const unsigned int end_idx = (offset + size + vmem->memslot_size - 1) / + vmem->memslot_size; + unsigned int idx; + + if (!vmem->dynamic_memslots) { + return; + } + + /* Activate all involved memslots in a single transaction. */ + memory_region_transaction_begin(); + for (idx = start_idx; idx < end_idx; idx++) { + virtio_mem_activate_memslot(vmem, idx); + } + memory_region_transaction_commit(); +} + +static void virtio_mem_deactivate_unplugged_memslots(VirtIOMEM *vmem, + uint64_t offset, + uint64_t size) +{ + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); + const unsigned int start_idx = offset / vmem->memslot_size; + const unsigned int end_idx = (offset + size + vmem->memslot_size - 1) / + vmem->memslot_size; + unsigned int idx; + + if (!vmem->dynamic_memslots) { + return; + } + + /* Deactivate all memslots with unplugged blocks in a single transaction. */ + memory_region_transaction_begin(); + for (idx = start_idx; idx < end_idx; idx++) { + const uint64_t memslot_offset = idx * vmem->memslot_size; + uint64_t memslot_size = vmem->memslot_size; + + /* The size of the last memslot might be smaller. */ + if (idx == vmem->nb_memslots - 1) { + memslot_size = region_size - memslot_offset; + } + + /* + * Partially covered memslots might still have some blocks plugged and + * have to remain active if that's the case. + */ + if (offset > memslot_offset || + offset + size < memslot_offset + memslot_size) { + const uint64_t gpa = vmem->addr + memslot_offset; + + if (!virtio_mem_is_range_unplugged(vmem, gpa, memslot_size)) { + continue; + } + } + + virtio_mem_deactivate_memslot(vmem, idx); + } + memory_region_transaction_commit(); +} + static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, uint64_t size, bool plug) { @@ -500,6 +597,8 @@ static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, } virtio_mem_notify_unplug(vmem, offset, size); virtio_mem_set_range_unplugged(vmem, start_gpa, size); + /* Deactivate completely unplugged memslots after updating the state. */ + virtio_mem_deactivate_unplugged_memslots(vmem, offset, size); return 0; } @@ -527,7 +626,20 @@ static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, } if (!ret) { + /* + * Activate before notifying and rollback in case of any errors. + * + * When activating a yet inactive memslot, memory notifiers will get + * notified about the added memory region and can register with the + * RamDiscardManager; this will traverse all plugged blocks and skip the + * blocks we are plugging here. The following notification will inform + * registered listeners about the blocks we're plugging. + */ + virtio_mem_activate_memslots_to_plug(vmem, offset, size); ret = virtio_mem_notify_plug(vmem, offset, size); + if (ret) { + virtio_mem_deactivate_unplugged_memslots(vmem, offset, size); + } } if (ret) { /* Could be preallocation or a notifier populated memory. */ @@ -620,6 +732,7 @@ static void virtio_mem_resize_usable_region(VirtIOMEM *vmem, static int virtio_mem_unplug_all(VirtIOMEM *vmem) { + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); RAMBlock *rb = vmem->memdev->mr.ram_block; if (vmem->size) { @@ -634,6 +747,9 @@ static int virtio_mem_unplug_all(VirtIOMEM *vmem) bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size); vmem->size = 0; notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); + + /* Deactivate all memslots after updating the state. */ + virtio_mem_deactivate_unplugged_memslots(vmem, 0, region_size); } trace_virtio_mem_unplugged_all(); @@ -790,6 +906,49 @@ static void virtio_mem_system_reset(void *opaque) virtio_mem_unplug_all(vmem); } +static void virtio_mem_prepare_mr(VirtIOMEM *vmem) +{ + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); + + assert(!vmem->mr && vmem->dynamic_memslots); + vmem->mr = g_new0(MemoryRegion, 1); + memory_region_init(vmem->mr, OBJECT(vmem), "virtio-mem", + region_size); + vmem->mr->align = memory_region_get_alignment(&vmem->memdev->mr); +} + +static void virtio_mem_prepare_memslots(VirtIOMEM *vmem) +{ + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); + unsigned int idx; + + g_assert(!vmem->memslots && vmem->nb_memslots && vmem->dynamic_memslots); + vmem->memslots = g_new0(MemoryRegion, vmem->nb_memslots); + + /* Initialize our memslots, but don't map them yet. */ + for (idx = 0; idx < vmem->nb_memslots; idx++) { + const uint64_t memslot_offset = idx * vmem->memslot_size; + uint64_t memslot_size = vmem->memslot_size; + char name[20]; + + /* The size of the last memslot might be smaller. */ + if (idx == vmem->nb_memslots - 1) { + memslot_size = region_size - memslot_offset; + } + + snprintf(name, sizeof(name), "memslot-%u", idx); + memory_region_init_alias(&vmem->memslots[idx], OBJECT(vmem), name, + &vmem->memdev->mr, memslot_offset, + memslot_size); + /* + * We want to be able to atomically and efficiently activate/deactivate + * individual memslots without affecting adjacent memslots in memory + * notifiers. + */ + memory_region_set_unmergeable(&vmem->memslots[idx], true); + } +} + static void virtio_mem_device_realize(DeviceState *dev, Error **errp) { MachineState *ms = MACHINE(qdev_get_machine()); @@ -861,6 +1020,14 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) vmem->unplugged_inaccessible = ON_OFF_AUTO_ON; #endif /* VIRTIO_MEM_HAS_LEGACY_GUESTS */ + if (vmem->dynamic_memslots && + vmem->unplugged_inaccessible != ON_OFF_AUTO_ON) { + error_setg(errp, "'%s' property set to 'on' requires '%s' to be 'on'", + VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP, + VIRTIO_MEM_UNPLUGGED_INACCESSIBLE_PROP); + return; + } + /* * If the block size wasn't configured by the user, use a sane default. This * allows using hugetlbfs backends of any page size without manual @@ -930,6 +1097,25 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) virtio_init(vdev, VIRTIO_ID_MEM, sizeof(struct virtio_mem_config)); vmem->vq = virtio_add_queue(vdev, 128, virtio_mem_handle_request); + /* + * With "dynamic-memslots=off" (old behavior) we always map the whole + * RAM memory region directly. + */ + if (vmem->dynamic_memslots) { + if (!vmem->mr) { + virtio_mem_prepare_mr(vmem); + } + if (vmem->nb_memslots <= 1) { + vmem->nb_memslots = 1; + vmem->memslot_size = memory_region_size(&vmem->memdev->mr); + } + if (!vmem->memslots) { + virtio_mem_prepare_memslots(vmem); + } + } else { + assert(!vmem->mr && !vmem->nb_memslots && !vmem->memslots); + } + host_memory_backend_set_mapped(vmem->memdev, true); vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem)); if (vmem->early_migration) { @@ -969,7 +1155,7 @@ static void virtio_mem_device_unrealize(DeviceState *dev) ram_block_coordinated_discard_require(false); } -static int virtio_mem_discard_range_cb(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_discard_range_cb(VirtIOMEM *vmem, void *arg, uint64_t offset, uint64_t size) { RAMBlock *rb = vmem->memdev->mr.ram_block; @@ -984,13 +1170,32 @@ static int virtio_mem_restore_unplugged(VirtIOMEM *vmem) virtio_mem_discard_range_cb); } -static int virtio_mem_post_load(void *opaque, int version_id) +static int virtio_mem_activate_memslot_range_cb(VirtIOMEM *vmem, void *arg, + uint64_t offset, uint64_t size) +{ + virtio_mem_activate_memslots_to_plug(vmem, offset, size); + return 0; +} + +static int virtio_mem_post_load_bitmap(VirtIOMEM *vmem) { - VirtIOMEM *vmem = VIRTIO_MEM(opaque); RamDiscardListener *rdl; int ret; /* + * We restored the bitmap and updated the requested size; activate all + * memslots (so listeners register) before notifying about plugged blocks. + */ + if (vmem->dynamic_memslots) { + /* + * We don't expect any active memslots at this point to deactivate: no + * memory was plugged on the migration destination. + */ + virtio_mem_for_each_plugged_range(vmem, NULL, + virtio_mem_activate_memslot_range_cb); + } + + /* * We started out with all memory discarded and our memory region is mapped * into an address space. Replay, now that we updated the bitmap. */ @@ -1001,6 +1206,20 @@ static int virtio_mem_post_load(void *opaque, int version_id) return ret; } } + return 0; +} + +static int virtio_mem_post_load(void *opaque, int version_id) +{ + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + int ret; + + if (!vmem->early_migration) { + ret = virtio_mem_post_load_bitmap(vmem); + if (ret) { + return ret; + } + } /* * If shared RAM is migrated using the file content and not using QEMU, @@ -1021,7 +1240,7 @@ static int virtio_mem_post_load(void *opaque, int version_id) return virtio_mem_restore_unplugged(vmem); } -static int virtio_mem_prealloc_range_cb(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_prealloc_range_cb(VirtIOMEM *vmem, void *arg, uint64_t offset, uint64_t size) { void *area = memory_region_get_ram_ptr(&vmem->memdev->mr) + offset; @@ -1043,7 +1262,7 @@ static int virtio_mem_post_load_early(void *opaque, int version_id) int ret; if (!vmem->prealloc) { - return 0; + goto post_load_bitmap; } /* @@ -1051,7 +1270,7 @@ static int virtio_mem_post_load_early(void *opaque, int version_id) * don't mess with preallocation and postcopy. */ if (migrate_ram_is_ignored(rb)) { - return 0; + goto post_load_bitmap; } /* @@ -1084,7 +1303,10 @@ static int virtio_mem_post_load_early(void *opaque, int version_id) return -EBUSY; } } - return 0; + +post_load_bitmap: + /* Finally, update any other state to be consistent with the new bitmap. */ + return virtio_mem_post_load_bitmap(vmem); } typedef struct VirtIOMEMMigSanityChecks { @@ -1235,11 +1457,79 @@ static MemoryRegion *virtio_mem_get_memory_region(VirtIOMEM *vmem, Error **errp) if (!vmem->memdev) { error_setg(errp, "'%s' property must be set", VIRTIO_MEM_MEMDEV_PROP); return NULL; + } else if (vmem->dynamic_memslots) { + if (!vmem->mr) { + virtio_mem_prepare_mr(vmem); + } + return vmem->mr; } return &vmem->memdev->mr; } +static void virtio_mem_decide_memslots(VirtIOMEM *vmem, unsigned int limit) +{ + uint64_t region_size, memslot_size, min_memslot_size; + unsigned int memslots; + RAMBlock *rb; + + if (!vmem->dynamic_memslots) { + return; + } + + /* We're called exactly once, before realizing the device. */ + assert(!vmem->nb_memslots); + + /* If realizing the device will fail, just assume a single memslot. */ + if (limit <= 1 || !vmem->memdev || !vmem->memdev->mr.ram_block) { + vmem->nb_memslots = 1; + return; + } + + rb = vmem->memdev->mr.ram_block; + region_size = memory_region_size(&vmem->memdev->mr); + + /* + * Determine the default block size now, to determine the minimum memslot + * size. We want the minimum slot size to be at least the device block size. + */ + if (!vmem->block_size) { + vmem->block_size = virtio_mem_default_block_size(rb); + } + /* If realizing the device will fail, just assume a single memslot. */ + if (vmem->block_size < qemu_ram_pagesize(rb) || + !QEMU_IS_ALIGNED(region_size, vmem->block_size)) { + vmem->nb_memslots = 1; + return; + } + + /* + * All memslots except the last one have a reasonable minimum size, and + * and all memslot sizes are aligned to the device block size. + */ + memslot_size = QEMU_ALIGN_UP(region_size / limit, vmem->block_size); + min_memslot_size = MAX(vmem->block_size, VIRTIO_MEM_MIN_MEMSLOT_SIZE); + memslot_size = MAX(memslot_size, min_memslot_size); + + memslots = QEMU_ALIGN_UP(region_size, memslot_size) / memslot_size; + if (memslots != 1) { + vmem->memslot_size = memslot_size; + } + vmem->nb_memslots = memslots; +} + +static unsigned int virtio_mem_get_memslots(VirtIOMEM *vmem) +{ + if (!vmem->dynamic_memslots) { + /* Exactly one static RAM memory region. */ + return 1; + } + + /* We're called after instructed to make a decision. */ + g_assert(vmem->nb_memslots); + return vmem->nb_memslots; +} + static void virtio_mem_add_size_change_notifier(VirtIOMEM *vmem, Notifier *notifier) { @@ -1377,6 +1667,21 @@ static void virtio_mem_instance_init(Object *obj) NULL, NULL); } +static void virtio_mem_instance_finalize(Object *obj) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + + /* + * Note: the core already dropped the references on all memory regions + * (it's passed as the owner to memory_region_init_*()) and finalized + * these objects. We can simply free the memory. + */ + g_free(vmem->memslots); + vmem->memslots = NULL; + g_free(vmem->mr); + vmem->mr = NULL; +} + static Property virtio_mem_properties[] = { DEFINE_PROP_UINT64(VIRTIO_MEM_ADDR_PROP, VirtIOMEM, addr, 0), DEFINE_PROP_UINT32(VIRTIO_MEM_NODE_PROP, VirtIOMEM, node, 0), @@ -1389,6 +1694,8 @@ static Property virtio_mem_properties[] = { #endif DEFINE_PROP_BOOL(VIRTIO_MEM_EARLY_MIGRATION_PROP, VirtIOMEM, early_migration, true), + DEFINE_PROP_BOOL(VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP, VirtIOMEM, + dynamic_memslots, false), DEFINE_PROP_END_OF_LIST(), }; @@ -1556,6 +1863,8 @@ static void virtio_mem_class_init(ObjectClass *klass, void *data) vmc->fill_device_info = virtio_mem_fill_device_info; vmc->get_memory_region = virtio_mem_get_memory_region; + vmc->decide_memslots = virtio_mem_decide_memslots; + vmc->get_memslots = virtio_mem_get_memslots; vmc->add_size_change_notifier = virtio_mem_add_size_change_notifier; vmc->remove_size_change_notifier = virtio_mem_remove_size_change_notifier; vmc->unplug_request_check = virtio_mem_unplug_request_check; @@ -1573,6 +1882,7 @@ static const TypeInfo virtio_mem_info = { .parent = TYPE_VIRTIO_DEVICE, .instance_size = sizeof(VirtIOMEM), .instance_init = virtio_mem_instance_init, + .instance_finalize = virtio_mem_instance_finalize, .class_init = virtio_mem_class_init, .class_size = sizeof(VirtIOMEMClass), .interfaces = (InterfaceInfo[]) { diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 605b160..30c376a 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -83,6 +83,21 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length); ram_addr_t qemu_ram_addr_from_host(void *ptr); ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr); RAMBlock *qemu_ram_block_by_name(const char *name); + +/* + * Translates a host ptr back to a RAMBlock and an offset in that RAMBlock. + * + * @ptr: The host pointer to translate. + * @round_offset: Whether to round the result offset down to a target page + * @offset: Will be set to the offset within the returned RAMBlock. + * + * Returns: RAMBlock (or NULL if not found) + * + * By the time this function returns, the returned pointer is not protected + * by RCU anymore. If the caller is not within an RCU critical section and + * does not hold the iothread lock, it must have other means of protecting the + * pointer, such as a reference to the memory region that owns the RAMBlock. + */ RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset, ram_addr_t *offset); ram_addr_t qemu_ram_block_host_offset(RAMBlock *rb, void *host); diff --git a/include/exec/memory.h b/include/exec/memory.h index c99842d..653a32e 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -95,6 +95,7 @@ struct ReservedRegion { * relative to the region's address space * @readonly: writes to this section are ignored * @nonvolatile: this section is non-volatile + * @unmergeable: this section should not get merged with adjacent sections */ struct MemoryRegionSection { Int128 size; @@ -104,6 +105,7 @@ struct MemoryRegionSection { hwaddr offset_within_address_space; bool readonly; bool nonvolatile; + bool unmergeable; }; typedef struct IOMMUTLBEntry IOMMUTLBEntry; @@ -599,8 +601,9 @@ typedef void (*ReplayRamDiscard)(MemoryRegionSection *section, void *opaque); * populated (consuming memory), to be used/accessed by the VM. * * A #RamDiscardManager can only be set for a RAM #MemoryRegion while the - * #MemoryRegion isn't mapped yet; it cannot change while the #MemoryRegion is - * mapped. + * #MemoryRegion isn't mapped into an address space yet (either directly + * or via an alias); it cannot change while the #MemoryRegion is + * mapped into an address space. * * The #RamDiscardManager is intended to be used by technologies that are * incompatible with discarding of RAM (e.g., VFIO, which may pin all @@ -772,6 +775,7 @@ struct MemoryRegion { bool nonvolatile; bool rom_device; bool flush_coalesced_mmio; + bool unmergeable; uint8_t dirty_log_mask; bool is_iommu; RAMBlock *ram_block; @@ -2350,6 +2354,25 @@ void memory_region_set_size(MemoryRegion *mr, uint64_t size); void memory_region_set_alias_offset(MemoryRegion *mr, hwaddr offset); +/* + * memory_region_set_unmergeable: Set a memory region unmergeable + * + * Mark a memory region unmergeable, resulting in the memory region (or + * everything contained in a memory region container) not getting merged when + * simplifying the address space and notifying memory listeners. Consequently, + * memory listeners will never get notified about ranges that are larger than + * the original memory regions. + * + * This is primarily useful when multiple aliases to a RAM memory region are + * mapped into a memory region container, and updates (e.g., enable/disable or + * map/unmap) of individual memory region aliases are not supposed to affect + * other memory regions in the same container. + * + * @mr: the #MemoryRegion to be updated + * @unmergeable: whether to mark the #MemoryRegion unmergeable + */ +void memory_region_set_unmergeable(MemoryRegion *mr, bool unmergeable); + /** * memory_region_present: checks if an address relative to a @container * translates into #MemoryRegion within @container diff --git a/include/hw/boards.h b/include/hw/boards.h index 55a64a1..43a56dc 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -297,15 +297,27 @@ struct MachineClass { * DeviceMemoryState: * @base: address in guest physical address space where the memory * address space for memory devices starts - * @mr: address space container for memory devices + * @mr: memory region container for memory devices + * @as: address space for memory devices + * @listener: memory listener used to track used memslots in the address space * @dimm_size: the sum of plugged DIMMs' sizes * @used_region_size: the part of @mr already used by memory devices + * @required_memslots: the number of memslots required by memory devices + * @used_memslots: the number of memslots currently used by memory devices + * @memslot_auto_decision_active: whether any plugged memory device + * automatically decided to use more than + * one memslot */ typedef struct DeviceMemoryState { hwaddr base; MemoryRegion mr; + AddressSpace as; + MemoryListener listener; uint64_t dimm_size; uint64_t used_region_size; + unsigned int required_memslots; + unsigned int used_memslots; + unsigned int memslot_auto_decision_active; } DeviceMemoryState; /** diff --git a/include/hw/mem/memory-device.h b/include/hw/mem/memory-device.h index 48d2611..3354d6c 100644 --- a/include/hw/mem/memory-device.h +++ b/include/hw/mem/memory-device.h @@ -14,6 +14,7 @@ #define MEMORY_DEVICE_H #include "hw/qdev-core.h" +#include "qemu/typedefs.h" #include "qapi/qapi-types-machine.h" #include "qom/object.h" @@ -41,6 +42,17 @@ typedef struct MemoryDeviceState MemoryDeviceState; * successive memory regions are used, a covering memory region has to * be provided. Scattered memory regions are not supported for single * devices. + * + * The device memory region returned via @get_memory_region may either be a + * single RAM memory region or a memory region container with subregions + * that are RAM memory regions or aliases to RAM memory regions. Other + * memory regions or subregions are not supported. + * + * If the device memory region returned via @get_memory_region is a + * memory region container, it's supported to dynamically (un)map subregions + * as long as the number of memslots returned by @get_memslots() won't + * be exceeded and as long as all memory regions are of the same kind (e.g., + * all RAM or all ROM). */ struct MemoryDeviceClass { /* private */ @@ -89,6 +101,28 @@ struct MemoryDeviceClass { MemoryRegion *(*get_memory_region)(MemoryDeviceState *md, Error **errp); /* + * Optional: Instruct the memory device to decide how many memory slots + * it requires, not exceeding the given limit. + * + * Called exactly once when pre-plugging the memory device, before + * querying the number of memslots using @get_memslots the first time. + */ + void (*decide_memslots)(MemoryDeviceState *md, unsigned int limit); + + /* + * Optional for memory devices that require only a single memslot, + * required for all other memory devices: Return the number of memslots + * (distinct RAM memory regions in the device memory region) that are + * required by the device. + * + * If this function is not implemented, the assumption is "1". + * + * Called when (un)plugging the memory device, to check if the requirements + * can be satisfied, and to do proper accounting. + */ + unsigned int (*get_memslots)(MemoryDeviceState *md); + + /* * Optional: Return the desired minimum alignment of the device in guest * physical address space. The final alignment is computed based on this * alignment and the alignment requirements of the memory region. @@ -105,8 +139,31 @@ struct MemoryDeviceClass { MemoryDeviceInfo *info); }; +/* + * Traditionally, KVM/vhost in many setups supported 509 memslots, whereby + * 253 memslots were "reserved" for boot memory and other devices (such + * as PCI BARs, which can get mapped dynamically) and 256 memslots were + * dedicated for DIMMs. These magic numbers worked reliably in the past. + * + * Further, using many memslots can negatively affect performance, so setting + * the soft-limit of memslots used by memory devices to the traditional + * DIMM limit of 256 sounds reasonable. + * + * If we have less than 509 memslots, we will instruct memory devices that + * support automatically deciding how many memslots to use to only use a single + * one. + * + * Hotplugging vhost devices with at least 509 memslots is not expected to + * cause problems, not even when devices automatically decided how many memslots + * to use. + */ +#define MEMORY_DEVICES_SOFT_MEMSLOT_LIMIT 256 +#define MEMORY_DEVICES_SAFE_MAX_MEMSLOTS 509 + MemoryDeviceInfoList *qmp_memory_device_list(void); uint64_t get_plugged_memory_size(void); +unsigned int memory_devices_get_reserved_memslots(void); +bool memory_devices_memslot_auto_decision_active(void); void memory_device_pre_plug(MemoryDeviceState *md, MachineState *ms, const uint64_t *legacy_align, Error **errp); void memory_device_plug(MemoryDeviceState *md, MachineState *ms); diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h index 1860b54..96ccc18 100644 --- a/include/hw/virtio/vhost-backend.h +++ b/include/hw/virtio/vhost-backend.h @@ -86,9 +86,6 @@ typedef int (*vhost_set_vring_enable_op)(struct vhost_dev *dev, typedef bool (*vhost_requires_shm_log_op)(struct vhost_dev *dev); typedef int (*vhost_migration_done_op)(struct vhost_dev *dev, char *mac_addr); -typedef bool (*vhost_backend_can_merge_op)(struct vhost_dev *dev, - uint64_t start1, uint64_t size1, - uint64_t start2, uint64_t size2); typedef int (*vhost_vsock_set_guest_cid_op)(struct vhost_dev *dev, uint64_t guest_cid); typedef int (*vhost_vsock_set_running_op)(struct vhost_dev *dev, int start); @@ -108,8 +105,7 @@ typedef int (*vhost_crypto_create_session_op)(struct vhost_dev *dev, typedef int (*vhost_crypto_close_session_op)(struct vhost_dev *dev, uint64_t session_id); -typedef bool (*vhost_backend_mem_section_filter_op)(struct vhost_dev *dev, - MemoryRegionSection *section); +typedef bool (*vhost_backend_no_private_memslots_op)(struct vhost_dev *dev); typedef int (*vhost_get_inflight_fd_op)(struct vhost_dev *dev, uint16_t queue_size, @@ -138,6 +134,7 @@ typedef struct VhostOps { vhost_backend_init vhost_backend_init; vhost_backend_cleanup vhost_backend_cleanup; vhost_backend_memslots_limit vhost_backend_memslots_limit; + vhost_backend_no_private_memslots_op vhost_backend_no_private_memslots; vhost_net_set_backend_op vhost_net_set_backend; vhost_net_set_mtu_op vhost_net_set_mtu; vhost_scsi_set_endpoint_op vhost_scsi_set_endpoint; @@ -163,7 +160,6 @@ typedef struct VhostOps { vhost_set_vring_enable_op vhost_set_vring_enable; vhost_requires_shm_log_op vhost_requires_shm_log; vhost_migration_done_op vhost_migration_done; - vhost_backend_can_merge_op vhost_backend_can_merge; vhost_vsock_set_guest_cid_op vhost_vsock_set_guest_cid; vhost_vsock_set_running_op vhost_vsock_set_running; vhost_set_iotlb_callback_op vhost_set_iotlb_callback; @@ -172,7 +168,6 @@ typedef struct VhostOps { vhost_set_config_op vhost_set_config; vhost_crypto_create_session_op vhost_crypto_create_session; vhost_crypto_close_session_op vhost_crypto_close_session; - vhost_backend_mem_section_filter_op vhost_backend_mem_section_filter; vhost_get_inflight_fd_op vhost_get_inflight_fd; vhost_set_inflight_fd_op vhost_set_inflight_fd; vhost_dev_start_op vhost_dev_start; diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h index 6a173cb..c7e54676 100644 --- a/include/hw/virtio/vhost.h +++ b/include/hw/virtio/vhost.h @@ -315,7 +315,8 @@ uint64_t vhost_get_features(struct vhost_dev *hdev, const int *feature_bits, */ void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits, uint64_t features); -bool vhost_has_free_slot(void); +unsigned int vhost_get_max_memslots(void); +unsigned int vhost_get_free_memslots(void); int vhost_net_set_backend(struct vhost_dev *hdev, struct vhost_vring_file *file); diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h index ab0fe2b..5f5b02b 100644 --- a/include/hw/virtio/virtio-mem.h +++ b/include/hw/virtio/virtio-mem.h @@ -33,6 +33,7 @@ OBJECT_DECLARE_TYPE(VirtIOMEM, VirtIOMEMClass, #define VIRTIO_MEM_UNPLUGGED_INACCESSIBLE_PROP "unplugged-inaccessible" #define VIRTIO_MEM_EARLY_MIGRATION_PROP "x-early-migration" #define VIRTIO_MEM_PREALLOC_PROP "prealloc" +#define VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP "dynamic-memslots" struct VirtIOMEM { VirtIODevice parent_obj; @@ -44,7 +45,28 @@ struct VirtIOMEM { int32_t bitmap_size; unsigned long *bitmap; - /* assigned memory backend and memory region */ + /* + * With "dynamic-memslots=on": Device memory region in which we dynamically + * map the memslots. + */ + MemoryRegion *mr; + + /* + * With "dynamic-memslots=on": The individual memslots (aliases into the + * memory backend). + */ + MemoryRegion *memslots; + + /* With "dynamic-memslots=on": The total number of memslots. */ + uint16_t nb_memslots; + + /* + * With "dynamic-memslots=on": Size of one memslot (the size of the + * last one can differ). + */ + uint64_t memslot_size; + + /* Assigned memory backend with the RAM memory region. */ HostMemoryBackend *memdev; /* NUMA node */ @@ -82,6 +104,12 @@ struct VirtIOMEM { */ bool early_migration; + /* + * Whether we dynamically map (multiple, if possible) memslots instead of + * statically mapping the whole RAM memory region. + */ + bool dynamic_memslots; + /* notifiers to notify when "size" changes */ NotifierList size_change_notifiers; @@ -96,6 +124,8 @@ struct VirtIOMEMClass { /* public */ void (*fill_device_info)(const VirtIOMEM *vmen, VirtioMEMDeviceInfo *vi); MemoryRegion *(*get_memory_region)(VirtIOMEM *vmem, Error **errp); + void (*decide_memslots)(VirtIOMEM *vmem, unsigned int limit); + unsigned int (*get_memslots)(VirtIOMEM *vmem); void (*add_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier); void (*remove_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier); void (*unplug_request_check)(VirtIOMEM *vmem, Error **errp); diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index ee9025f..97a8a4f 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -215,7 +215,8 @@ typedef struct KVMRouteChange { /* external API */ -bool kvm_has_free_slot(MachineState *ms); +unsigned int kvm_get_max_memslots(void); +unsigned int kvm_get_free_memslots(void); bool kvm_has_sync_mmu(void); int kvm_has_vcpu_events(void); int kvm_has_robust_singlestep(void); @@ -552,7 +553,6 @@ int kvm_set_one_reg(CPUState *cs, uint64_t id, void *source); */ int kvm_get_one_reg(CPUState *cs, uint64_t id, void *target); struct ppc_radix_page_info *kvm_get_radix_page_info(void); -int kvm_get_max_memslots(void); /* Notify resamplefd for EOI of specific interrupts. */ void kvm_resample_fd_notify(int gsi); diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index a5b9122..075939a 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -40,6 +40,7 @@ typedef struct KVMMemoryUpdate { typedef struct KVMMemoryListener { MemoryListener listener; KVMSlot *slots; + unsigned int nr_used_slots; int as_id; QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_add; QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_del; diff --git a/stubs/qmp_memory_device.c b/stubs/memory_device.c index e75cac6..15fd93f 100644 --- a/stubs/qmp_memory_device.c +++ b/stubs/memory_device.c @@ -10,3 +10,13 @@ uint64_t get_plugged_memory_size(void) { return (uint64_t)-1; } + +unsigned int memory_devices_get_reserved_memslots(void) +{ + return 0; +} + +bool memory_devices_memslot_auto_decision_active(void) +{ + return false; +} diff --git a/stubs/meson.build b/stubs/meson.build index ef6e39a..cde4497 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -32,7 +32,7 @@ stub_ss.add(files('monitor.c')) stub_ss.add(files('monitor-core.c')) stub_ss.add(files('physmem.c')) stub_ss.add(files('qemu-timer-notify-cb.c')) -stub_ss.add(files('qmp_memory_device.c')) +stub_ss.add(files('memory_device.c')) stub_ss.add(files('qmp-command-available.c')) stub_ss.add(files('qmp-quit.c')) stub_ss.add(files('qtest.c')) diff --git a/system/memory.c b/system/memory.c index fa1c99f..a800fbc 100644 --- a/system/memory.c +++ b/system/memory.c @@ -224,6 +224,7 @@ struct FlatRange { bool romd_mode; bool readonly; bool nonvolatile; + bool unmergeable; }; #define FOR_EACH_FLAT_RANGE(var, view) \ @@ -240,6 +241,7 @@ section_from_flat_range(FlatRange *fr, FlatView *fv) .offset_within_address_space = int128_get64(fr->addr.start), .readonly = fr->readonly, .nonvolatile = fr->nonvolatile, + .unmergeable = fr->unmergeable, }; } @@ -250,7 +252,8 @@ static bool flatrange_equal(FlatRange *a, FlatRange *b) && a->offset_in_region == b->offset_in_region && a->romd_mode == b->romd_mode && a->readonly == b->readonly - && a->nonvolatile == b->nonvolatile; + && a->nonvolatile == b->nonvolatile + && a->unmergeable == b->unmergeable; } static FlatView *flatview_new(MemoryRegion *mr_root) @@ -323,7 +326,8 @@ static bool can_merge(FlatRange *r1, FlatRange *r2) && r1->dirty_log_mask == r2->dirty_log_mask && r1->romd_mode == r2->romd_mode && r1->readonly == r2->readonly - && r1->nonvolatile == r2->nonvolatile; + && r1->nonvolatile == r2->nonvolatile + && !r1->unmergeable && !r2->unmergeable; } /* Attempt to simplify a view by merging adjacent ranges */ @@ -599,7 +603,8 @@ static void render_memory_region(FlatView *view, Int128 base, AddrRange clip, bool readonly, - bool nonvolatile) + bool nonvolatile, + bool unmergeable) { MemoryRegion *subregion; unsigned i; @@ -616,6 +621,7 @@ static void render_memory_region(FlatView *view, int128_addto(&base, int128_make64(mr->addr)); readonly |= mr->readonly; nonvolatile |= mr->nonvolatile; + unmergeable |= mr->unmergeable; tmp = addrrange_make(base, mr->size); @@ -629,14 +635,14 @@ static void render_memory_region(FlatView *view, int128_subfrom(&base, int128_make64(mr->alias->addr)); int128_subfrom(&base, int128_make64(mr->alias_offset)); render_memory_region(view, mr->alias, base, clip, - readonly, nonvolatile); + readonly, nonvolatile, unmergeable); return; } /* Render subregions in priority order. */ QTAILQ_FOREACH(subregion, &mr->subregions, subregions_link) { render_memory_region(view, subregion, base, clip, - readonly, nonvolatile); + readonly, nonvolatile, unmergeable); } if (!mr->terminates) { @@ -652,6 +658,7 @@ static void render_memory_region(FlatView *view, fr.romd_mode = mr->romd_mode; fr.readonly = readonly; fr.nonvolatile = nonvolatile; + fr.unmergeable = unmergeable; /* Render the region itself into any gaps left by the current view. */ for (i = 0; i < view->nr && int128_nz(remain); ++i) { @@ -753,7 +760,7 @@ static FlatView *generate_memory_topology(MemoryRegion *mr) if (mr) { render_memory_region(view, mr, int128_zero(), addrrange_make(int128_zero(), int128_2_64()), - false, false); + false, false, false); } flatview_simplify(view); @@ -2085,7 +2092,7 @@ int memory_region_iommu_num_indexes(IOMMUMemoryRegion *iommu_mr) RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr) { - if (!memory_region_is_mapped(mr) || !memory_region_is_ram(mr)) { + if (!memory_region_is_ram(mr)) { return NULL; } return mr->rdm; @@ -2094,7 +2101,7 @@ RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr) void memory_region_set_ram_discard_manager(MemoryRegion *mr, RamDiscardManager *rdm) { - g_assert(memory_region_is_ram(mr) && !memory_region_is_mapped(mr)); + g_assert(memory_region_is_ram(mr)); g_assert(!rdm || !mr->rdm); mr->rdm = rdm; } @@ -2755,6 +2762,18 @@ void memory_region_set_alias_offset(MemoryRegion *mr, hwaddr offset) memory_region_transaction_commit(); } +void memory_region_set_unmergeable(MemoryRegion *mr, bool unmergeable) +{ + if (unmergeable == mr->unmergeable) { + return; + } + + memory_region_transaction_begin(); + mr->unmergeable = unmergeable; + memory_region_update_pending |= mr->enabled; + memory_region_transaction_commit(); +} + uint64_t memory_region_get_alignment(const MemoryRegion *mr) { return mr->align; diff --git a/system/physmem.c b/system/physmem.c index edc3ed8..fc2b0fe 100644 --- a/system/physmem.c +++ b/system/physmem.c @@ -2221,23 +2221,6 @@ ram_addr_t qemu_ram_block_host_offset(RAMBlock *rb, void *host) return res; } -/* - * Translates a host ptr back to a RAMBlock, a ram_addr and an offset - * in that RAMBlock. - * - * ptr: Host pointer to look up - * round_offset: If true round the result offset down to a page boundary - * *ram_addr: set to result ram_addr - * *offset: set to result offset within the RAMBlock - * - * Returns: RAMBlock (or NULL if not found) - * - * By the time this function returns, the returned pointer is not protected - * by RCU anymore. If the caller is not within an RCU critical section and - * does not hold the iothread lock, it must have other means of protecting the - * pointer, such as a reference to the region that includes the incoming - * ram_addr_t. - */ RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset, ram_addr_t *offset) { |