2018-04-23 19:51:16 +03:00
|
|
|
/*
|
|
|
|
* Memory Device Interface
|
|
|
|
*
|
|
|
|
* Copyright (c) 2018 Red Hat, Inc.
|
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* David Hildenbrand <david@redhat.com>
|
|
|
|
*
|
|
|
|
* This work is licensed under the terms of the GNU GPL, version 2 or later.
|
|
|
|
* See the COPYING file in the top-level directory.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef MEMORY_DEVICE_H
|
|
|
|
#define MEMORY_DEVICE_H
|
|
|
|
|
2019-08-12 08:23:51 +03:00
|
|
|
#include "hw/qdev-core.h"
|
2020-09-13 22:53:46 +03:00
|
|
|
#include "qapi/qapi-types-machine.h"
|
2018-04-23 19:51:16 +03:00
|
|
|
#include "qom/object.h"
|
|
|
|
|
|
|
|
#define TYPE_MEMORY_DEVICE "memory-device"
|
|
|
|
|
2020-09-03 23:43:22 +03:00
|
|
|
typedef struct MemoryDeviceClass MemoryDeviceClass;
|
2020-09-01 00:07:33 +03:00
|
|
|
DECLARE_CLASS_CHECKERS(MemoryDeviceClass, MEMORY_DEVICE,
|
|
|
|
TYPE_MEMORY_DEVICE)
|
2018-04-23 19:51:16 +03:00
|
|
|
#define MEMORY_DEVICE(obj) \
|
|
|
|
INTERFACE_CHECK(MemoryDeviceState, (obj), TYPE_MEMORY_DEVICE)
|
|
|
|
|
2018-12-04 17:20:06 +03:00
|
|
|
typedef struct MemoryDeviceState MemoryDeviceState;
|
2018-04-23 19:51:16 +03:00
|
|
|
|
2018-10-05 12:20:16 +03:00
|
|
|
/**
|
|
|
|
* MemoryDeviceClass:
|
|
|
|
*
|
|
|
|
* All memory devices need to implement TYPE_MEMORY_DEVICE as an interface.
|
|
|
|
*
|
|
|
|
* A memory device is a device that owns a memory region which is
|
|
|
|
* mapped into guest physical address space at a certain address. The
|
|
|
|
* address in guest physical memory can either be specified explicitly
|
|
|
|
* or get assigned automatically.
|
2018-10-05 12:20:18 +03:00
|
|
|
*
|
2023-06-22 13:18:23 +03:00
|
|
|
* Some memory device might not own a memory region in certain device
|
|
|
|
* configurations. Such devices can logically get (un)plugged, however,
|
|
|
|
* empty memory devices are mostly ignored by the memory device code.
|
|
|
|
*
|
2018-10-05 12:20:18 +03:00
|
|
|
* Conceptually, memory devices only span one memory region. If multiple
|
|
|
|
* successive memory regions are used, a covering memory region has to
|
|
|
|
* be provided. Scattered memory regions are not supported for single
|
|
|
|
* devices.
|
2023-09-26 21:57:26 +03:00
|
|
|
*
|
|
|
|
* 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.
|
2023-09-26 21:57:29 +03:00
|
|
|
*
|
|
|
|
* 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).
|
2018-10-05 12:20:16 +03:00
|
|
|
*/
|
2020-09-03 23:43:22 +03:00
|
|
|
struct MemoryDeviceClass {
|
2018-10-05 12:20:16 +03:00
|
|
|
/* private */
|
2018-04-23 19:51:16 +03:00
|
|
|
InterfaceClass parent_class;
|
|
|
|
|
2018-10-05 12:20:16 +03:00
|
|
|
/*
|
|
|
|
* Return the address of the memory device in guest physical memory.
|
|
|
|
*
|
|
|
|
* Called when (un)plugging a memory device or when iterating over
|
|
|
|
* all memory devices mapped into guest physical address space.
|
|
|
|
*
|
|
|
|
* If "0" is returned, no address has been specified by the user and
|
|
|
|
* no address has been assigned to this memory device yet.
|
|
|
|
*/
|
2018-04-23 19:51:16 +03:00
|
|
|
uint64_t (*get_addr)(const MemoryDeviceState *md);
|
2018-10-05 12:20:16 +03:00
|
|
|
|
2018-10-05 12:20:20 +03:00
|
|
|
/*
|
|
|
|
* Set the address of the memory device in guest physical memory.
|
|
|
|
*
|
|
|
|
* Called when plugging the memory device to configure the determined
|
|
|
|
* address in guest physical memory.
|
|
|
|
*/
|
|
|
|
void (*set_addr)(MemoryDeviceState *md, uint64_t addr, Error **errp);
|
|
|
|
|
2018-10-05 12:20:16 +03:00
|
|
|
/*
|
|
|
|
* Return the amount of memory provided by the memory device currently
|
|
|
|
* usable ("plugged") by the VM.
|
|
|
|
*
|
|
|
|
* Called when calculating the total amount of ram available to the
|
|
|
|
* VM (e.g. to report memory stats to the user).
|
|
|
|
*
|
|
|
|
* This is helpful for devices that dynamically manage the amount of
|
|
|
|
* memory accessible by the guest via the reserved memory region. For
|
|
|
|
* most devices, this corresponds to the size of the memory region.
|
|
|
|
*/
|
2018-10-05 12:20:15 +03:00
|
|
|
uint64_t (*get_plugged_size)(const MemoryDeviceState *md, Error **errp);
|
2018-10-05 12:20:16 +03:00
|
|
|
|
2018-10-05 12:20:18 +03:00
|
|
|
/*
|
2023-06-22 13:18:23 +03:00
|
|
|
* Return the memory region of the memory device. If the device is
|
|
|
|
* completely empty, returns NULL without an error.
|
2018-10-05 12:20:18 +03:00
|
|
|
*
|
|
|
|
* Called when (un)plugging the memory device, to (un)map the
|
|
|
|
* memory region in guest physical memory, but also to detect the
|
|
|
|
* required alignment during address assignment or when the size of the
|
|
|
|
* memory region is required.
|
|
|
|
*/
|
|
|
|
MemoryRegion *(*get_memory_region)(MemoryDeviceState *md, Error **errp);
|
|
|
|
|
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>
2023-09-26 21:57:32 +03:00
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
|
2023-09-26 21:57:26 +03:00
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
|
2020-10-08 11:30:28 +03:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
* Called when plugging the memory device to detect the required alignment
|
|
|
|
* during address assignment.
|
|
|
|
*/
|
|
|
|
uint64_t (*get_min_alignment)(const MemoryDeviceState *md);
|
|
|
|
|
2018-10-05 12:20:16 +03:00
|
|
|
/*
|
|
|
|
* Translate the memory device into #MemoryDeviceInfo.
|
|
|
|
*/
|
2018-04-23 19:51:16 +03:00
|
|
|
void (*fill_device_info)(const MemoryDeviceState *md,
|
|
|
|
MemoryDeviceInfo *info);
|
2020-09-03 23:43:22 +03:00
|
|
|
};
|
2018-04-23 19:51:16 +03:00
|
|
|
|
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>
2023-09-26 21:57:32 +03:00
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
|
2018-04-23 19:51:16 +03:00
|
|
|
MemoryDeviceInfoList *qmp_memory_device_list(void);
|
|
|
|
uint64_t get_plugged_memory_size(void);
|
2023-09-26 21:57:29 +03:00
|
|
|
unsigned int memory_devices_get_reserved_memslots(void);
|
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>
2023-09-26 21:57:32 +03:00
|
|
|
bool memory_devices_memslot_auto_decision_active(void);
|
2018-10-05 12:20:21 +03:00
|
|
|
void memory_device_pre_plug(MemoryDeviceState *md, MachineState *ms,
|
|
|
|
const uint64_t *legacy_align, Error **errp);
|
2018-10-05 12:20:22 +03:00
|
|
|
void memory_device_plug(MemoryDeviceState *md, MachineState *ms);
|
2018-10-05 12:20:23 +03:00
|
|
|
void memory_device_unplug(MemoryDeviceState *md, MachineState *ms);
|
2018-10-05 12:20:17 +03:00
|
|
|
uint64_t memory_device_get_region_size(const MemoryDeviceState *md,
|
|
|
|
Error **errp);
|
2018-04-23 19:51:16 +03:00
|
|
|
|
|
|
|
#endif
|