2019-05-19 13:07:45 +01:00
|
|
|
# SPDX-License-Identifier: GPL-2.0-only
|
2022-06-22 08:38:36 +02:00
|
|
|
config VIRTIO_ANCHOR
|
|
|
|
|
bool
|
|
|
|
|
|
2007-10-22 11:03:36 +10:00
|
|
|
config VIRTIO
|
2008-02-04 23:50:05 -05:00
|
|
|
tristate
|
2022-06-22 08:38:36 +02:00
|
|
|
select VIRTIO_ANCHOR
|
2020-06-14 01:50:22 +09:00
|
|
|
help
|
2012-09-28 15:05:15 +09:30
|
|
|
This option is selected by any driver which implements the virtio
|
2017-08-16 19:31:57 +02:00
|
|
|
bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
|
|
|
|
|
or CONFIG_S390_GUEST.
|
2007-10-22 11:03:40 +10:00
|
|
|
|
2021-01-04 14:55:00 +08:00
|
|
|
config VIRTIO_PCI_LIB
|
|
|
|
|
tristate
|
|
|
|
|
help
|
|
|
|
|
Modern PCI device implementation. This module implements the
|
|
|
|
|
basic probe and control for devices which are based on modern
|
|
|
|
|
PCI device with possible vendor specific extensions. Any
|
|
|
|
|
module that selects this module must depend on PCI.
|
|
|
|
|
|
2021-10-29 17:14:42 +08:00
|
|
|
config VIRTIO_PCI_LIB_LEGACY
|
|
|
|
|
tristate
|
|
|
|
|
help
|
|
|
|
|
Legacy PCI device (Virtio PCI Card 0.9.x Draft and older device)
|
|
|
|
|
implementation.
|
|
|
|
|
This module implements the basic probe and control for devices
|
|
|
|
|
which are based on legacy PCI device. Any module that selects this
|
|
|
|
|
module must depend on PCI.
|
|
|
|
|
|
2018-01-07 12:33:56 +01:00
|
|
|
menuconfig VIRTIO_MENU
|
|
|
|
|
bool "Virtio drivers"
|
|
|
|
|
default y
|
|
|
|
|
|
|
|
|
|
if VIRTIO_MENU
|
2011-07-05 17:06:14 +03:00
|
|
|
|
2022-06-22 09:29:40 +08:00
|
|
|
config VIRTIO_HARDEN_NOTIFICATION
|
|
|
|
|
bool "Harden virtio notification"
|
2022-06-30 15:10:57 -04:00
|
|
|
depends on BROKEN
|
2022-06-22 09:29:40 +08:00
|
|
|
help
|
|
|
|
|
Enable this to harden the device notifications and suppress
|
|
|
|
|
those that happen at a time where notifications are illegal.
|
|
|
|
|
|
2022-06-30 15:10:57 -04:00
|
|
|
Experimental: Note that several drivers still have issues that
|
2022-06-22 09:29:40 +08:00
|
|
|
may cause crashes or hangs when correct handling of
|
|
|
|
|
notifications is enforced; depending on the subset of
|
|
|
|
|
drivers and devices you use, this may or may not work.
|
|
|
|
|
|
|
|
|
|
If unsure, say N.
|
|
|
|
|
|
2007-11-12 21:30:26 -06:00
|
|
|
config VIRTIO_PCI
|
2012-10-02 11:19:07 -07:00
|
|
|
tristate "PCI driver for virtio devices"
|
|
|
|
|
depends on PCI
|
2021-01-04 14:55:00 +08:00
|
|
|
select VIRTIO_PCI_LIB
|
2007-11-12 21:30:26 -06:00
|
|
|
select VIRTIO
|
2020-06-14 01:50:22 +09:00
|
|
|
help
|
2015-01-15 14:15:51 +02:00
|
|
|
This driver provides support for virtio based paravirtual device
|
2007-11-12 21:30:26 -06:00
|
|
|
drivers over PCI. This requires that your VMM has appropriate PCI
|
|
|
|
|
virtio backends. Most QEMU based VMMs should support these devices
|
|
|
|
|
(like KVM or Xen).
|
|
|
|
|
|
|
|
|
|
If unsure, say M.
|
|
|
|
|
|
2023-12-19 11:32:43 +02:00
|
|
|
config VIRTIO_PCI_ADMIN_LEGACY
|
|
|
|
|
bool
|
|
|
|
|
depends on VIRTIO_PCI && (X86 || COMPILE_TEST)
|
|
|
|
|
default y
|
|
|
|
|
|
2015-01-15 16:06:26 +02:00
|
|
|
config VIRTIO_PCI_LEGACY
|
|
|
|
|
bool "Support for legacy virtio draft 0.9.X and older devices"
|
|
|
|
|
default y
|
|
|
|
|
depends on VIRTIO_PCI
|
2021-10-29 17:14:42 +08:00
|
|
|
select VIRTIO_PCI_LIB_LEGACY
|
2020-06-14 01:50:22 +09:00
|
|
|
help
|
2015-01-15 16:06:26 +02:00
|
|
|
Virtio PCI Card 0.9.X Draft (circa 2014) and older device support.
|
|
|
|
|
|
|
|
|
|
This option enables building a transitional driver, supporting
|
|
|
|
|
both devices conforming to Virtio 1 specification, and legacy devices.
|
|
|
|
|
If disabled, you get a slightly smaller, non-transitional driver,
|
|
|
|
|
with no legacy compatibility.
|
|
|
|
|
|
|
|
|
|
So look out into your driveway. Do you have a flying car? If
|
|
|
|
|
so, you can happily disable this option and virtio will not
|
|
|
|
|
break. Otherwise, leave it set. Unless you're testing what
|
|
|
|
|
life will be like in The Future.
|
|
|
|
|
|
|
|
|
|
If unsure, say Y.
|
|
|
|
|
|
2020-03-26 22:01:22 +08:00
|
|
|
config VIRTIO_VDPA
|
|
|
|
|
tristate "vDPA driver for virtio devices"
|
2020-04-12 04:36:55 -04:00
|
|
|
depends on VDPA
|
2020-03-26 22:01:22 +08:00
|
|
|
select VIRTIO
|
|
|
|
|
help
|
|
|
|
|
This driver provides support for virtio based paravirtual
|
|
|
|
|
device driver over vDPA bus. For this to be useful, you need
|
|
|
|
|
an appropriate vDPA device implementation that operates on a
|
|
|
|
|
physical device to allow the datapath of virtio to be
|
|
|
|
|
offloaded to hardware.
|
|
|
|
|
|
|
|
|
|
If unsure, say M.
|
|
|
|
|
|
2019-07-05 19:33:23 +05:30
|
|
|
config VIRTIO_PMEM
|
|
|
|
|
tristate "Support for virtio pmem driver"
|
|
|
|
|
depends on VIRTIO
|
|
|
|
|
depends on LIBNVDIMM
|
|
|
|
|
help
|
|
|
|
|
This driver provides access to virtio-pmem devices, storage devices
|
|
|
|
|
that are mapped into the physical address space - similar to NVDIMMs
|
|
|
|
|
- with a virtio-based flushing interface.
|
|
|
|
|
|
|
|
|
|
If unsure, say Y.
|
|
|
|
|
|
2008-02-04 23:50:12 -05:00
|
|
|
config VIRTIO_BALLOON
|
2012-09-28 15:05:14 +09:30
|
|
|
tristate "Virtio balloon driver"
|
|
|
|
|
depends on VIRTIO
|
2014-10-09 15:29:32 -07:00
|
|
|
select MEMORY_BALLOON
|
2020-04-06 20:05:05 -07:00
|
|
|
select PAGE_REPORTING
|
2020-06-14 01:50:22 +09:00
|
|
|
help
|
2008-02-04 23:50:12 -05:00
|
|
|
This driver supports increasing and decreasing the amount
|
|
|
|
|
of memory within a KVM guest.
|
|
|
|
|
|
|
|
|
|
If unsure, say M.
|
|
|
|
|
|
virtio-mem: Paravirtualized memory hotplug
Each virtio-mem device owns exactly one memory region. It is responsible
for adding/removing memory from that memory region on request.
When the device driver starts up, the requested amount of memory is
queried and then plugged to Linux. On request, further memory can be
plugged or unplugged. This patch only implements the plugging part.
On x86-64, memory can currently be plugged in 4MB ("subblock") granularity.
When required, a new memory block will be added (e.g., usually 128MB on
x86-64) in order to plug more subblocks. Only x86-64 was tested for now.
The online_page callback is used to keep unplugged subblocks offline
when onlining memory - similar to the Hyper-V balloon driver. Unplugged
pages are marked PG_offline, to tell dump tools (e.g., makedumpfile) to
skip them.
User space is usually responsible for onlining the added memory. The
memory hotplug notifier is used to synchronize virtio-mem activity
against memory onlining/offlining.
Each virtio-mem device can belong to a NUMA node, which allows us to
easily add/remove small chunks of memory to/from a specific NUMA node by
using multiple virtio-mem devices. Something that works even when the
guest has no idea about the NUMA topology.
One way to view virtio-mem is as a "resizable DIMM" or a DIMM with many
"sub-DIMMS".
This patch directly introduces the basic infrastructure to implement memory
unplug. Especially the memory block states and subblock bitmaps will be
heavily used there.
Notes:
- In case memory is to be onlined by user space, we limit the amount of
offline memory blocks, to not run out of memory. This is esp. an
issue if memory is added faster than it is getting onlined.
- Suspend/Hibernate is not supported due to the way virtio-mem devices
behave. Limited support might be possible in the future.
- Reloading the device driver is not supported.
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Tested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: linux-acpi@vger.kernel.org
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200507140139.17083-2-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2020-05-07 16:01:25 +02:00
|
|
|
config VIRTIO_MEM
|
|
|
|
|
tristate "Virtio mem driver"
|
virtio-mem: s390 support
Now that s390 code is prepared for memory devices that reside above the
maximum storage increment exposed through SCLP, everything is in place
to unlock virtio-mem support.
As virtio-mem in Linux currently supports logically onlining/offlining
memory in pageblock granularity, we have an effective hot(un)plug
granularity of 1 MiB on s390.
As virito-mem adds/removes individual Linux memory blocks (256MB), we
will currently never use gigantic pages in the identity mapping.
It is worth noting that neither storage keys nor storage attributes (e.g.,
data / nodat) are touched when onlining memory blocks, which is good
because we are not supposed to touch these parts for unplugged device
blocks that are logically offline in Linux.
We will currently never initialize storage keys for virtio-mem
memory -- IOW, storage_key_init_range() is never called. It could be added
in the future when plugging device blocks. But as that function
essentially does nothing without modifying the code (changing
PAGE_DEFAULT_ACC), that's just fine for now.
kexec should work as intended and just like on other architectures that
support virtio-mem: we will never place kexec binaries on virtio-mem
memory, and never indicate virtio-mem memory to the 2nd kernel. The
device driver in the 2nd kernel can simply reset the device --
turning all memory unplugged, to then start plugging memory and adding
them to Linux, without causing trouble because the memory is already
used elsewhere.
The special s390 kdump mode, whereby the 2nd kernel creates the ELF
core header, won't currently dump virtio-mem memory. The virtio-mem
driver has a special kdump mode, from where we can detect memory ranges
to dump. Based on this, support for dumping virtio-mem memory can be
added in the future fairly easily.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Mario Casquero <mcasquer@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Tested-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Link: https://lore.kernel.org/r/20241025141453.1210600-5-david@redhat.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
2024-10-25 16:14:49 +02:00
|
|
|
depends on X86_64 || ARM64 || RISCV || S390
|
virtio-mem: Paravirtualized memory hotplug
Each virtio-mem device owns exactly one memory region. It is responsible
for adding/removing memory from that memory region on request.
When the device driver starts up, the requested amount of memory is
queried and then plugged to Linux. On request, further memory can be
plugged or unplugged. This patch only implements the plugging part.
On x86-64, memory can currently be plugged in 4MB ("subblock") granularity.
When required, a new memory block will be added (e.g., usually 128MB on
x86-64) in order to plug more subblocks. Only x86-64 was tested for now.
The online_page callback is used to keep unplugged subblocks offline
when onlining memory - similar to the Hyper-V balloon driver. Unplugged
pages are marked PG_offline, to tell dump tools (e.g., makedumpfile) to
skip them.
User space is usually responsible for onlining the added memory. The
memory hotplug notifier is used to synchronize virtio-mem activity
against memory onlining/offlining.
Each virtio-mem device can belong to a NUMA node, which allows us to
easily add/remove small chunks of memory to/from a specific NUMA node by
using multiple virtio-mem devices. Something that works even when the
guest has no idea about the NUMA topology.
One way to view virtio-mem is as a "resizable DIMM" or a DIMM with many
"sub-DIMMS".
This patch directly introduces the basic infrastructure to implement memory
unplug. Especially the memory block states and subblock bitmaps will be
heavily used there.
Notes:
- In case memory is to be onlined by user space, we limit the amount of
offline memory blocks, to not run out of memory. This is esp. an
issue if memory is added faster than it is getting onlined.
- Suspend/Hibernate is not supported due to the way virtio-mem devices
behave. Limited support might be possible in the future.
- Reloading the device driver is not supported.
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Tested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: linux-acpi@vger.kernel.org
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200507140139.17083-2-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2020-05-07 16:01:25 +02:00
|
|
|
depends on VIRTIO
|
2021-11-05 13:44:24 -07:00
|
|
|
depends on MEMORY_HOTPLUG
|
virtio-mem: Paravirtualized memory hotplug
Each virtio-mem device owns exactly one memory region. It is responsible
for adding/removing memory from that memory region on request.
When the device driver starts up, the requested amount of memory is
queried and then plugged to Linux. On request, further memory can be
plugged or unplugged. This patch only implements the plugging part.
On x86-64, memory can currently be plugged in 4MB ("subblock") granularity.
When required, a new memory block will be added (e.g., usually 128MB on
x86-64) in order to plug more subblocks. Only x86-64 was tested for now.
The online_page callback is used to keep unplugged subblocks offline
when onlining memory - similar to the Hyper-V balloon driver. Unplugged
pages are marked PG_offline, to tell dump tools (e.g., makedumpfile) to
skip them.
User space is usually responsible for onlining the added memory. The
memory hotplug notifier is used to synchronize virtio-mem activity
against memory onlining/offlining.
Each virtio-mem device can belong to a NUMA node, which allows us to
easily add/remove small chunks of memory to/from a specific NUMA node by
using multiple virtio-mem devices. Something that works even when the
guest has no idea about the NUMA topology.
One way to view virtio-mem is as a "resizable DIMM" or a DIMM with many
"sub-DIMMS".
This patch directly introduces the basic infrastructure to implement memory
unplug. Especially the memory block states and subblock bitmaps will be
heavily used there.
Notes:
- In case memory is to be onlined by user space, we limit the amount of
offline memory blocks, to not run out of memory. This is esp. an
issue if memory is added faster than it is getting onlined.
- Suspend/Hibernate is not supported due to the way virtio-mem devices
behave. Limited support might be possible in the future.
- Reloading the device driver is not supported.
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Tested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: linux-acpi@vger.kernel.org
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200507140139.17083-2-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2020-05-07 16:01:25 +02:00
|
|
|
depends on MEMORY_HOTREMOVE
|
2020-06-19 16:03:33 +08:00
|
|
|
depends on CONTIG_ALLOC
|
2021-11-08 18:35:53 -08:00
|
|
|
depends on EXCLUSIVE_SYSTEM_RAM
|
virtio-mem: Paravirtualized memory hotplug
Each virtio-mem device owns exactly one memory region. It is responsible
for adding/removing memory from that memory region on request.
When the device driver starts up, the requested amount of memory is
queried and then plugged to Linux. On request, further memory can be
plugged or unplugged. This patch only implements the plugging part.
On x86-64, memory can currently be plugged in 4MB ("subblock") granularity.
When required, a new memory block will be added (e.g., usually 128MB on
x86-64) in order to plug more subblocks. Only x86-64 was tested for now.
The online_page callback is used to keep unplugged subblocks offline
when onlining memory - similar to the Hyper-V balloon driver. Unplugged
pages are marked PG_offline, to tell dump tools (e.g., makedumpfile) to
skip them.
User space is usually responsible for onlining the added memory. The
memory hotplug notifier is used to synchronize virtio-mem activity
against memory onlining/offlining.
Each virtio-mem device can belong to a NUMA node, which allows us to
easily add/remove small chunks of memory to/from a specific NUMA node by
using multiple virtio-mem devices. Something that works even when the
guest has no idea about the NUMA topology.
One way to view virtio-mem is as a "resizable DIMM" or a DIMM with many
"sub-DIMMS".
This patch directly introduces the basic infrastructure to implement memory
unplug. Especially the memory block states and subblock bitmaps will be
heavily used there.
Notes:
- In case memory is to be onlined by user space, we limit the amount of
offline memory blocks, to not run out of memory. This is esp. an
issue if memory is added faster than it is getting onlined.
- Suspend/Hibernate is not supported due to the way virtio-mem devices
behave. Limited support might be possible in the future.
- Reloading the device driver is not supported.
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Tested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: linux-acpi@vger.kernel.org
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200507140139.17083-2-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2020-05-07 16:01:25 +02:00
|
|
|
help
|
|
|
|
|
This driver provides access to virtio-mem paravirtualized memory
|
|
|
|
|
devices, allowing to hotplug and hotunplug memory.
|
|
|
|
|
|
virtio-mem: s390 support
Now that s390 code is prepared for memory devices that reside above the
maximum storage increment exposed through SCLP, everything is in place
to unlock virtio-mem support.
As virtio-mem in Linux currently supports logically onlining/offlining
memory in pageblock granularity, we have an effective hot(un)plug
granularity of 1 MiB on s390.
As virito-mem adds/removes individual Linux memory blocks (256MB), we
will currently never use gigantic pages in the identity mapping.
It is worth noting that neither storage keys nor storage attributes (e.g.,
data / nodat) are touched when onlining memory blocks, which is good
because we are not supposed to touch these parts for unplugged device
blocks that are logically offline in Linux.
We will currently never initialize storage keys for virtio-mem
memory -- IOW, storage_key_init_range() is never called. It could be added
in the future when plugging device blocks. But as that function
essentially does nothing without modifying the code (changing
PAGE_DEFAULT_ACC), that's just fine for now.
kexec should work as intended and just like on other architectures that
support virtio-mem: we will never place kexec binaries on virtio-mem
memory, and never indicate virtio-mem memory to the 2nd kernel. The
device driver in the 2nd kernel can simply reset the device --
turning all memory unplugged, to then start plugging memory and adding
them to Linux, without causing trouble because the memory is already
used elsewhere.
The special s390 kdump mode, whereby the 2nd kernel creates the ELF
core header, won't currently dump virtio-mem memory. The virtio-mem
driver has a special kdump mode, from where we can detect memory ranges
to dump. Based on this, support for dumping virtio-mem memory can be
added in the future fairly easily.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Mario Casquero <mcasquer@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Tested-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Link: https://lore.kernel.org/r/20241025141453.1210600-5-david@redhat.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
2024-10-25 16:14:49 +02:00
|
|
|
This driver currently supports x86-64, arm64, riscv and s390.
|
|
|
|
|
Although it should compile on other architectures that implement
|
|
|
|
|
memory hot(un)plug, architecture-specific and/or common
|
|
|
|
|
code changes may be required for virtio-mem, kdump and kexec to
|
|
|
|
|
work as expected.
|
virtio-mem: Paravirtualized memory hotplug
Each virtio-mem device owns exactly one memory region. It is responsible
for adding/removing memory from that memory region on request.
When the device driver starts up, the requested amount of memory is
queried and then plugged to Linux. On request, further memory can be
plugged or unplugged. This patch only implements the plugging part.
On x86-64, memory can currently be plugged in 4MB ("subblock") granularity.
When required, a new memory block will be added (e.g., usually 128MB on
x86-64) in order to plug more subblocks. Only x86-64 was tested for now.
The online_page callback is used to keep unplugged subblocks offline
when onlining memory - similar to the Hyper-V balloon driver. Unplugged
pages are marked PG_offline, to tell dump tools (e.g., makedumpfile) to
skip them.
User space is usually responsible for onlining the added memory. The
memory hotplug notifier is used to synchronize virtio-mem activity
against memory onlining/offlining.
Each virtio-mem device can belong to a NUMA node, which allows us to
easily add/remove small chunks of memory to/from a specific NUMA node by
using multiple virtio-mem devices. Something that works even when the
guest has no idea about the NUMA topology.
One way to view virtio-mem is as a "resizable DIMM" or a DIMM with many
"sub-DIMMS".
This patch directly introduces the basic infrastructure to implement memory
unplug. Especially the memory block states and subblock bitmaps will be
heavily used there.
Notes:
- In case memory is to be onlined by user space, we limit the amount of
offline memory blocks, to not run out of memory. This is esp. an
issue if memory is added faster than it is getting onlined.
- Suspend/Hibernate is not supported due to the way virtio-mem devices
behave. Limited support might be possible in the future.
- Reloading the device driver is not supported.
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Tested-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: linux-acpi@vger.kernel.org
Signed-off-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20200507140139.17083-2-david@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2020-05-07 16:01:25 +02:00
|
|
|
|
|
|
|
|
If unsure, say M.
|
|
|
|
|
|
2015-03-27 12:46:12 +10:30
|
|
|
config VIRTIO_INPUT
|
|
|
|
|
tristate "Virtio input driver"
|
|
|
|
|
depends on VIRTIO
|
|
|
|
|
depends on INPUT
|
2020-06-14 01:50:22 +09:00
|
|
|
help
|
2015-03-27 12:46:12 +10:30
|
|
|
This driver supports virtio input devices such as
|
|
|
|
|
keyboards, mice and tablets.
|
|
|
|
|
|
|
|
|
|
If unsure, say M.
|
|
|
|
|
|
2019-04-03 16:04:09 +01:00
|
|
|
config VIRTIO_MMIO
|
2012-10-02 11:19:07 -07:00
|
|
|
tristate "Platform bus driver for memory mapped virtio devices"
|
2016-02-02 21:46:36 -08:00
|
|
|
depends on HAS_IOMEM && HAS_DMA
|
2019-04-03 16:04:09 +01:00
|
|
|
select VIRTIO
|
2020-06-14 01:50:22 +09:00
|
|
|
help
|
2019-04-03 16:04:09 +01:00
|
|
|
This drivers provides support for memory mapped virtio
|
2011-10-24 14:07:03 +01:00
|
|
|
platform device driver.
|
|
|
|
|
|
|
|
|
|
If unsure, say N.
|
|
|
|
|
|
2012-05-09 18:30:16 +01:00
|
|
|
config VIRTIO_MMIO_CMDLINE_DEVICES
|
|
|
|
|
bool "Memory mapped virtio devices parameter parsing"
|
|
|
|
|
depends on VIRTIO_MMIO
|
2020-06-14 01:50:22 +09:00
|
|
|
help
|
2012-05-09 18:30:16 +01:00
|
|
|
Allow virtio-mmio devices instantiation via the kernel command line
|
|
|
|
|
or module parameters. Be aware that using incorrect parameters (base
|
|
|
|
|
address in particular) can crash your system - you have been warned.
|
2016-10-18 10:12:27 -02:00
|
|
|
See Documentation/admin-guide/kernel-parameters.rst for details.
|
2012-05-09 18:30:16 +01:00
|
|
|
|
|
|
|
|
If unsure, say 'N'.
|
|
|
|
|
|
2020-08-19 12:10:11 +09:00
|
|
|
config VIRTIO_DMA_SHARED_BUFFER
|
|
|
|
|
tristate
|
|
|
|
|
depends on DMA_SHARED_BUFFER
|
|
|
|
|
help
|
|
|
|
|
This option adds a flavor of dma buffers that are backed by
|
|
|
|
|
virtio resources.
|
|
|
|
|
|
2024-04-24 12:40:45 +02:00
|
|
|
config VIRTIO_DEBUG
|
|
|
|
|
bool "Debug facilities"
|
|
|
|
|
depends on VIRTIO
|
|
|
|
|
help
|
|
|
|
|
Enable this to expose debug facilities over debugfs.
|
|
|
|
|
This allows to debug features, to see what features the device
|
|
|
|
|
advertises and to set filter for features used by driver.
|
|
|
|
|
|
|
|
|
|
If unsure, say N.
|
|
|
|
|
|
2025-05-09 18:07:22 +02:00
|
|
|
config VIRTIO_RTC
|
|
|
|
|
tristate "Virtio RTC driver"
|
|
|
|
|
depends on VIRTIO
|
|
|
|
|
depends on PTP_1588_CLOCK_OPTIONAL
|
|
|
|
|
help
|
|
|
|
|
This driver provides current time from a Virtio RTC device. The driver
|
virtio_rtc: Add PTP clocks
Expose the virtio_rtc clocks as PTP clocks to userspace, similar to
ptp_kvm. virtio_rtc can expose multiple clocks, e.g. a UTC clock and a
monotonic clock.
Userspace should distinguish different clocks through the name assigned by
the driver. In particular, UTC-like clocks can also be distinguished by if
and how leap seconds are smeared. udev rules such as the following can be
used to get different symlinks for different clock types:
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 0/variant 0", SYMLINK += "ptp_virtio"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 1/variant 0", SYMLINK += "ptp_virtio_tai"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 2/variant 0", SYMLINK += "ptp_virtio_monotonic"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 0", SYMLINK += "ptp_virtio_smear_unspecified"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 1", SYMLINK += "ptp_virtio_smear_noon_linear"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 2", SYMLINK += "ptp_virtio_smear_sls"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 4/variant 0", SYMLINK += "ptp_virtio_maybe_smeared"
The preferred PTP clock reading method is ioctl PTP_SYS_OFFSET_PRECISE2,
through the ptp_clock_info.getcrosststamp() op. For now,
PTP_SYS_OFFSET_PRECISE2 will return -EOPNOTSUPP through a weak function.
PTP_SYS_OFFSET_PRECISE2 requires cross-timestamping support for specific
clocksources, which will be added in the following. If the clocksource
specific code is enabled, check that the Virtio RTC device supports the
respective HW counter before obtaining an actual cross-timestamp from the
Virtio device.
The Virtio RTC device response time may be higher than the timekeeper
seqcount increment interval. Therefore, obtain the cross-timestamp before
calling get_device_system_crosststamp().
As a fallback, support the ioctl PTP_SYS_OFFSET_EXTENDED2 for all
platforms.
Assume that concurrency issues during PTP clock removal are avoided by the
posix_clock framework.
Kconfig recursive dependencies prevent virtio_rtc from implicitly enabling
PTP_1588_CLOCK, therefore just warn the user if PTP_1588_CLOCK is not
available. Since virtio_rtc should in the future also expose clocks as RTC
class devices, do not depend VIRTIO_RTC on PTP_1588_CLOCK.
Signed-off-by: Peter Hilber <quic_philber@quicinc.com>
Message-Id: <20250509160734.1772-3-quic_philber@quicinc.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2025-05-09 18:07:23 +02:00
|
|
|
provides the time through one or more clocks. The Virtio RTC PTP
|
2025-05-09 18:07:25 +02:00
|
|
|
clocks and/or the Real Time Clock driver for Virtio RTC must be
|
|
|
|
|
enabled to expose the clocks to userspace.
|
2025-05-09 18:07:22 +02:00
|
|
|
|
|
|
|
|
To compile this code as a module, choose M here: the module will be
|
|
|
|
|
called virtio_rtc.
|
|
|
|
|
|
|
|
|
|
If unsure, say M.
|
|
|
|
|
|
virtio_rtc: Add PTP clocks
Expose the virtio_rtc clocks as PTP clocks to userspace, similar to
ptp_kvm. virtio_rtc can expose multiple clocks, e.g. a UTC clock and a
monotonic clock.
Userspace should distinguish different clocks through the name assigned by
the driver. In particular, UTC-like clocks can also be distinguished by if
and how leap seconds are smeared. udev rules such as the following can be
used to get different symlinks for different clock types:
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 0/variant 0", SYMLINK += "ptp_virtio"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 1/variant 0", SYMLINK += "ptp_virtio_tai"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 2/variant 0", SYMLINK += "ptp_virtio_monotonic"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 0", SYMLINK += "ptp_virtio_smear_unspecified"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 1", SYMLINK += "ptp_virtio_smear_noon_linear"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 2", SYMLINK += "ptp_virtio_smear_sls"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 4/variant 0", SYMLINK += "ptp_virtio_maybe_smeared"
The preferred PTP clock reading method is ioctl PTP_SYS_OFFSET_PRECISE2,
through the ptp_clock_info.getcrosststamp() op. For now,
PTP_SYS_OFFSET_PRECISE2 will return -EOPNOTSUPP through a weak function.
PTP_SYS_OFFSET_PRECISE2 requires cross-timestamping support for specific
clocksources, which will be added in the following. If the clocksource
specific code is enabled, check that the Virtio RTC device supports the
respective HW counter before obtaining an actual cross-timestamp from the
Virtio device.
The Virtio RTC device response time may be higher than the timekeeper
seqcount increment interval. Therefore, obtain the cross-timestamp before
calling get_device_system_crosststamp().
As a fallback, support the ioctl PTP_SYS_OFFSET_EXTENDED2 for all
platforms.
Assume that concurrency issues during PTP clock removal are avoided by the
posix_clock framework.
Kconfig recursive dependencies prevent virtio_rtc from implicitly enabling
PTP_1588_CLOCK, therefore just warn the user if PTP_1588_CLOCK is not
available. Since virtio_rtc should in the future also expose clocks as RTC
class devices, do not depend VIRTIO_RTC on PTP_1588_CLOCK.
Signed-off-by: Peter Hilber <quic_philber@quicinc.com>
Message-Id: <20250509160734.1772-3-quic_philber@quicinc.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2025-05-09 18:07:23 +02:00
|
|
|
if VIRTIO_RTC
|
|
|
|
|
|
2025-05-09 18:07:25 +02:00
|
|
|
comment "WARNING: Consider enabling VIRTIO_RTC_PTP and/or VIRTIO_RTC_CLASS."
|
|
|
|
|
depends on !VIRTIO_RTC_PTP && !VIRTIO_RTC_CLASS
|
virtio_rtc: Add PTP clocks
Expose the virtio_rtc clocks as PTP clocks to userspace, similar to
ptp_kvm. virtio_rtc can expose multiple clocks, e.g. a UTC clock and a
monotonic clock.
Userspace should distinguish different clocks through the name assigned by
the driver. In particular, UTC-like clocks can also be distinguished by if
and how leap seconds are smeared. udev rules such as the following can be
used to get different symlinks for different clock types:
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 0/variant 0", SYMLINK += "ptp_virtio"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 1/variant 0", SYMLINK += "ptp_virtio_tai"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 2/variant 0", SYMLINK += "ptp_virtio_monotonic"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 0", SYMLINK += "ptp_virtio_smear_unspecified"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 1", SYMLINK += "ptp_virtio_smear_noon_linear"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 2", SYMLINK += "ptp_virtio_smear_sls"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 4/variant 0", SYMLINK += "ptp_virtio_maybe_smeared"
The preferred PTP clock reading method is ioctl PTP_SYS_OFFSET_PRECISE2,
through the ptp_clock_info.getcrosststamp() op. For now,
PTP_SYS_OFFSET_PRECISE2 will return -EOPNOTSUPP through a weak function.
PTP_SYS_OFFSET_PRECISE2 requires cross-timestamping support for specific
clocksources, which will be added in the following. If the clocksource
specific code is enabled, check that the Virtio RTC device supports the
respective HW counter before obtaining an actual cross-timestamp from the
Virtio device.
The Virtio RTC device response time may be higher than the timekeeper
seqcount increment interval. Therefore, obtain the cross-timestamp before
calling get_device_system_crosststamp().
As a fallback, support the ioctl PTP_SYS_OFFSET_EXTENDED2 for all
platforms.
Assume that concurrency issues during PTP clock removal are avoided by the
posix_clock framework.
Kconfig recursive dependencies prevent virtio_rtc from implicitly enabling
PTP_1588_CLOCK, therefore just warn the user if PTP_1588_CLOCK is not
available. Since virtio_rtc should in the future also expose clocks as RTC
class devices, do not depend VIRTIO_RTC on PTP_1588_CLOCK.
Signed-off-by: Peter Hilber <quic_philber@quicinc.com>
Message-Id: <20250509160734.1772-3-quic_philber@quicinc.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2025-05-09 18:07:23 +02:00
|
|
|
|
|
|
|
|
comment "Enable PTP_1588_CLOCK in order to enable VIRTIO_RTC_PTP."
|
|
|
|
|
depends on PTP_1588_CLOCK=n
|
|
|
|
|
|
|
|
|
|
config VIRTIO_RTC_PTP
|
|
|
|
|
bool "Virtio RTC PTP clocks"
|
|
|
|
|
default y
|
|
|
|
|
depends on PTP_1588_CLOCK
|
|
|
|
|
help
|
|
|
|
|
This exposes any Virtio RTC clocks as PTP Hardware Clocks (PHCs) to
|
|
|
|
|
userspace. The PHC sysfs attribute "clock_name" describes the clock
|
|
|
|
|
type.
|
|
|
|
|
|
|
|
|
|
If unsure, say Y.
|
|
|
|
|
|
2025-05-09 18:07:24 +02:00
|
|
|
config VIRTIO_RTC_ARM
|
|
|
|
|
bool "Virtio RTC cross-timestamping using Arm Generic Timer"
|
|
|
|
|
default y
|
|
|
|
|
depends on VIRTIO_RTC_PTP && ARM_ARCH_TIMER
|
|
|
|
|
help
|
|
|
|
|
This enables Virtio RTC cross-timestamping using the Arm Generic Timer.
|
|
|
|
|
It only has an effect if the Virtio RTC device also supports this. The
|
|
|
|
|
cross-timestamp is available through the PTP clock driver precise
|
|
|
|
|
cross-timestamp ioctl (PTP_SYS_OFFSET_PRECISE2 aka
|
|
|
|
|
PTP_SYS_OFFSET_PRECISE).
|
|
|
|
|
|
|
|
|
|
If unsure, say Y.
|
|
|
|
|
|
2025-05-09 18:07:25 +02:00
|
|
|
comment "Enable RTC_CLASS in order to enable VIRTIO_RTC_CLASS."
|
|
|
|
|
depends on RTC_CLASS=n
|
|
|
|
|
|
|
|
|
|
config VIRTIO_RTC_CLASS
|
|
|
|
|
bool "Real Time Clock driver for Virtio RTC"
|
|
|
|
|
default y
|
|
|
|
|
depends on RTC_CLASS
|
|
|
|
|
help
|
|
|
|
|
This exposes the Virtio RTC UTC-like clock as a Linux Real Time Clock.
|
|
|
|
|
It only has an effect if the Virtio RTC device has a UTC-like clock
|
|
|
|
|
which smears leap seconds to avoid steps. The Real Time Clock is
|
|
|
|
|
read-only, and may support setting an alarm.
|
|
|
|
|
|
|
|
|
|
If unsure, say Y.
|
|
|
|
|
|
virtio_rtc: Add PTP clocks
Expose the virtio_rtc clocks as PTP clocks to userspace, similar to
ptp_kvm. virtio_rtc can expose multiple clocks, e.g. a UTC clock and a
monotonic clock.
Userspace should distinguish different clocks through the name assigned by
the driver. In particular, UTC-like clocks can also be distinguished by if
and how leap seconds are smeared. udev rules such as the following can be
used to get different symlinks for different clock types:
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 0/variant 0", SYMLINK += "ptp_virtio"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 1/variant 0", SYMLINK += "ptp_virtio_tai"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 2/variant 0", SYMLINK += "ptp_virtio_monotonic"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 0", SYMLINK += "ptp_virtio_smear_unspecified"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 1", SYMLINK += "ptp_virtio_smear_noon_linear"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 3/variant 2", SYMLINK += "ptp_virtio_smear_sls"
SUBSYSTEM=="ptp", ATTR{clock_name}=="Virtio PTP type 4/variant 0", SYMLINK += "ptp_virtio_maybe_smeared"
The preferred PTP clock reading method is ioctl PTP_SYS_OFFSET_PRECISE2,
through the ptp_clock_info.getcrosststamp() op. For now,
PTP_SYS_OFFSET_PRECISE2 will return -EOPNOTSUPP through a weak function.
PTP_SYS_OFFSET_PRECISE2 requires cross-timestamping support for specific
clocksources, which will be added in the following. If the clocksource
specific code is enabled, check that the Virtio RTC device supports the
respective HW counter before obtaining an actual cross-timestamp from the
Virtio device.
The Virtio RTC device response time may be higher than the timekeeper
seqcount increment interval. Therefore, obtain the cross-timestamp before
calling get_device_system_crosststamp().
As a fallback, support the ioctl PTP_SYS_OFFSET_EXTENDED2 for all
platforms.
Assume that concurrency issues during PTP clock removal are avoided by the
posix_clock framework.
Kconfig recursive dependencies prevent virtio_rtc from implicitly enabling
PTP_1588_CLOCK, therefore just warn the user if PTP_1588_CLOCK is not
available. Since virtio_rtc should in the future also expose clocks as RTC
class devices, do not depend VIRTIO_RTC on PTP_1588_CLOCK.
Signed-off-by: Peter Hilber <quic_philber@quicinc.com>
Message-Id: <20250509160734.1772-3-quic_philber@quicinc.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2025-05-09 18:07:23 +02:00
|
|
|
endif # VIRTIO_RTC
|
|
|
|
|
|
2018-01-07 12:33:56 +01:00
|
|
|
endif # VIRTIO_MENU
|