| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
guest_memfd
Commit 852f0048f3 ("RAMBlock: make guest_memfd require uncoordinated
discard") highlighted that subsystems like VFIO may disable RAM block
discard. However, guest_memfd relies on discard operations for page
conversion between private and shared memory, potentially leading to
the stale IOMMU mapping issue when assigning hardware devices to
confidential VMs via shared memory. To address this and allow shared
device assignement, it is crucial to ensure the VFIO system refreshes
its IOMMU mappings.
RamDiscardManager is an existing interface (used by virtio-mem) to
adjust VFIO mappings in relation to VM page assignment. Effectively page
conversion is similar to hot-removing a page in one mode and adding it
back in the other. Therefore, similar actions are required for page
conversion events. Introduce the RamDiscardManager to guest_memfd to
facilitate this process.
Since guest_memfd is not an object, it cannot directly implement the
RamDiscardManager interface. Implementing it in HostMemoryBackend is
not appropriate because guest_memfd is per RAMBlock, and some RAMBlocks
have a memory backend while others do not. Notably, virtual BIOS
RAMBlocks using memory_region_init_ram_guest_memfd() do not have a
backend.
To manage RAMBlocks with guest_memfd, define a new object named
RamBlockAttributes to implement the RamDiscardManager interface. This
object can store the guest_memfd information such as the bitmap for
shared memory and the registered listeners for event notifications. A
new state_change() helper function is provided to notify listeners, such
as VFIO, allowing VFIO to do dynamically DMA map and unmap for the shared
memory according to conversion events. Note that in the current context
of RamDiscardManager for guest_memfd, the shared state is analogous to
being populated, while the private state can be considered discarded for
simplicity. In the future, it would be more complicated if considering
more states like private/shared/discarded at the same time.
In current implementation, memory state tracking is performed at the
host page size granularity, as the minimum conversion size can be one
page per request. Additionally, VFIO expected the DMA mapping for a
specific IOVA to be mapped and unmapped with the same granularity.
Confidential VMs may perform partial conversions, such as conversions on
small regions within a larger one. To prevent such invalid cases and
until support for DMA mapping cut operations is available, all
operations are performed with 4K granularity.
In addition, memory conversion failures cause QEMU to quit rather than
resuming the guest or retrying the operation at present. It would be
future work to add more error handling or rollback mechanisms once
conversion failures are allowed. For example, in-place conversion of
guest_memfd could retry the unmap operation during the conversion from
shared to private. For now, keep the complex error handling out of the
picture as it is not required.
Tested-by: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Link: https://lore.kernel.org/r/20250612082747.51539-5-chenyi.qiang@intel.com
[peterx: squash fixup from Chenyi to fix builds]
Signed-off-by: Peter Xu <peterx@redhat.com>
|
|
Create MAP_SHARED RAMBlocks by mmap'ing a file descriptor rather than using
MAP_ANON, so the memory can be accessed in another process by passing and
mmap'ing the fd. This will allow CPR to support memory-backend-ram and
memory-backend-shm objects, provided the user creates them with share=on.
Use memfd_create if available because it has no constraints. If not, use
POSIX shm_open. However, allocation on the opened fd may fail if the shm
mount size is too small, even if the system has free memory, so for backwards
compatibility fall back to qemu_anon_ram_alloc/MAP_ANON on failure.
For backwards compatibility on Windows, always use MAP_ANON. share=on has
no purpose there, but the syntax is accepted, and must continue to work.
Lastly, quietly fall back to MAP_ANON if the system does not support
qemu_ram_alloc_from_fd.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/1736967650-129648-5-git-send-email-steven.sistare@oracle.com
Signed-off-by: Fabiano Rosas <farosas@suse.de>
|
|
The dma-helpers.c file is in the system/ subdirectory, but it
defines its trace events in the root trace-events file. Move
them to the system/trace-events file where they more naturally
belong.
Fixes: 800d4deda0 ("softmmu: move more files to softmmu/")
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20241108162909.4080314-2-peter.maydell@linaro.org
|
|
Move cpu-throttle.c from system to migration since it's
only used for migration; this makes us avoid exporting the
util functions and variables in misc.h but export them in
migration.h when implementing the periodic ramblock dirty
sync feature in the upcoming commits.
Since CPU throttle timers are only used in migration, move
their registry to migration_object_init.
Signed-off-by: Hyman Huang <yong.huang@smartx.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/c1b3efaa0cb49e03d422e9da97bdb65cc3d234d1.1729146786.git.yong.huang@smartx.com
[peterx: Fix build on MacOS on cocoa.m, not move cpu-throttle.h yet]
[peterx: Fix subject spelling, per pm215]
Signed-off-by: Peter Xu <peterx@redhat.com>
|
|
Right now migration_throttle() tracepoint lacks very important
important information, i.e. no one could easily say how much the guest
is throttled. This makes difficult to debug guest quality of service
during migration.
This patch adds one more tracepoint into cpu_throttle_set() which is
actually doing this job.
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Peter Xu <peterx@redhat.com>
CC: Fabiano Rosas <farosas@suse.de>
CC: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20240905191941.310592-1-den@openvz.org
Signed-off-by: Peter Xu <peterx@redhat.com>
|
|
They don't need to be in the global trace-events file and can have a
local trace header. Also add address_space_map tracepoint for tracking
mapping behaviour.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20240705084047.857176-4-alex.bennee@linaro.org>
|
|
The softmmu/ directory contains files specific to system
emulation. Rename it as system/. Update meson rules, the
MAINTAINERS file and all the documentation and comments.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20231004090629.37473-14-philmd@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
