diff options
Diffstat (limited to 'hw/mem/memory-device.c')
| -rw-r--r-- | hw/mem/memory-device.c | 196 |
1 files changed, 188 insertions, 8 deletions
diff --git a/hw/mem/memory-device.c b/hw/mem/memory-device.c index 667d56bd29..ae38f48f16 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 = { |