aboutsummaryrefslogtreecommitdiff
path: root/hw/mem
diff options
context:
space:
mode:
authorDavid Hildenbrand <david@redhat.com>2023-09-26 20:57:32 +0200
committerDavid Hildenbrand <david@redhat.com>2023-10-12 14:15:22 +0200
commita2335113aeda1cddad3dc4a76f2ace47a00d7ac9 (patch)
treeded2d02e09f97f97ca040f18d7d31d37e5fa28b0 /hw/mem
parentcd89c065b06d49691ecb1f3707849472acdf3ea5 (diff)
downloadqemu-a2335113aeda1cddad3dc4a76f2ace47a00d7ac9.zip
qemu-a2335113aeda1cddad3dc4a76f2ace47a00d7ac9.tar.gz
qemu-a2335113aeda1cddad3dc4a76f2ace47a00d7ac9.tar.bz2
memory-device,vhost: Support automatic decision on the number of memslots
We want to support memory devices that can automatically decide how many memslots they will use. In the worst case, they have to use a single memslot. The target use cases are virtio-mem and the hyper-v balloon. Let's calculate a reasonable limit such a memory device may use, and instruct the device to make a decision based on that limit. Use a simple heuristic that considers: * A memslot soft-limit for all memory devices of 256; also, to not consume too many memslots -- which could harm performance. * Actually still free and unreserved memslots * The percentage of the remaining device memory region that memory device will occupy. Further, while we properly check before plugging a memory device whether there still is are free memslots, we have other memslot consumers (such as boot memory, PCI BARs) that don't perform any checks and might dynamically consume memslots without any prior reservation. So we might succeed in plugging a memory device, but once we dynamically map a PCI BAR we would be in trouble. Doing accounting / reservation / checks for all such users is problematic (e.g., sometimes we might temporarily split boot memory into two memslots, triggered by the BIOS). We use the historic magic memslot number of 509 as orientation to when supporting 256 memory devices -> memslots (leaving 253 for boot memory and other devices) has been proven to work reliable. We'll fallback to suggesting a single memslot if we don't have at least 509 total memslots. Plugging vhost devices with less than 509 memslots available while we have memory devices plugged that consume multiple memslots due to automatic decisions can be problematic. Most configurations might just fail due to "limit < used + reserved", however, it can also happen that these memory devices would suddenly consume memslots that would actually be required by other memslot consumers (boot, PCI BARs) later. Note that this has always been sketchy with vhost devices that support only a small number of memslots; but we don't want to make it any worse.So let's keep it simple and simply reject plugging such vhost devices in such a configuration. Eventually, all vhost devices that want to be fully compatible with such memory devices should support a decent number of memslots (>= 509). Message-ID: <20230926185738.277351-13-david@redhat.com> Reviewed-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: David Hildenbrand <david@redhat.com>
Diffstat (limited to 'hw/mem')
-rw-r--r--hw/mem/memory-device.c96
1 files changed, 93 insertions, 3 deletions
diff --git a/hw/mem/memory-device.c b/hw/mem/memory-device.c
index 1b14ba5..ae38f48 100644
--- a/hw/mem/memory-device.c
+++ b/hw/mem/memory-device.c
@@ -85,13 +85,93 @@ unsigned int memory_devices_get_reserved_memslots(void)
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 required_memslots = memory_device_get_memslots(md);
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 memory slots for kvm and vhost */
if (kvm_enabled() &&
@@ -300,6 +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;
@@ -311,7 +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 += memory_device_get_memslots(md);
+ 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);
@@ -320,6 +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;
/*
@@ -330,8 +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 -= memory_device_get_memslots(md);
+ ms->device_memory->required_memslots -= memslots;
trace_memory_device_unplug(DEVICE(md)->id ? DEVICE(md)->id : "",
mdc->get_addr(md));
}