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>

1 files changed, 57 insertions, 0 deletions

diff --git a/include/hw/mem/memory-device.h b/include/hw/mem/memory-device.h
index 48d2611fc5..3354d6c166 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);