mirror of
https://github.com/Motorhead1991/qemu.git
synced 2025-07-26 03:43:58 -06:00
5d6483edaa
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>
57 lines
3.9 KiB
Text
57 lines
3.9 KiB
Text
# See docs/devel/tracing.rst for syntax documentation.
|
|
|
|
# balloon.c
|
|
# Since requests are raised via monitor, not many tracepoints are needed.
|
|
balloon_event(void *opaque, unsigned long addr) "opaque %p addr %lu"
|
|
|
|
# dma-helpers.c
|
|
dma_blk_io(void *dbs, void *bs, int64_t offset, bool to_dev) "dbs=%p bs=%p offset=%" PRId64 " to_dev=%d"
|
|
dma_aio_cancel(void *dbs) "dbs=%p"
|
|
dma_complete(void *dbs, int ret, void *cb) "dbs=%p ret=%d cb=%p"
|
|
dma_blk_cb(void *dbs, int ret) "dbs=%p ret=%d"
|
|
dma_map_wait(void *dbs) "dbs=%p"
|
|
|
|
# ioport.c
|
|
cpu_in(unsigned int addr, char size, unsigned int val) "addr 0x%x(%c) value %u"
|
|
cpu_out(unsigned int addr, char size, unsigned int val) "addr 0x%x(%c) value %u"
|
|
|
|
# memory.c
|
|
memory_region_ops_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size, const char *name) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u name '%s'"
|
|
memory_region_ops_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size, const char *name) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u name '%s'"
|
|
memory_region_subpage_read(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" value 0x%"PRIx64" size %u"
|
|
memory_region_subpage_write(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" value 0x%"PRIx64" size %u"
|
|
memory_region_ram_device_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
|
|
memory_region_ram_device_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
|
|
memory_region_sync_dirty(const char *mr, const char *listener, int global) "mr '%s' listener '%s' synced (global=%d)"
|
|
flatview_new(void *view, void *root) "%p (root %p)"
|
|
flatview_destroy(void *view, void *root) "%p (root %p)"
|
|
flatview_destroy_rcu(void *view, void *root) "%p (root %p)"
|
|
global_dirty_changed(unsigned int bitmask) "bitmask 0x%"PRIx32
|
|
|
|
# physmem.c
|
|
address_space_map(void *as, uint64_t addr, uint64_t len, bool is_write, uint32_t attrs) "as:%p addr 0x%"PRIx64":%"PRIx64" write:%d attrs:0x%x"
|
|
find_ram_offset(uint64_t size, uint64_t offset) "size: 0x%" PRIx64 " @ 0x%" PRIx64
|
|
find_ram_offset_loop(uint64_t size, uint64_t candidate, uint64_t offset, uint64_t next, uint64_t mingap) "trying size: 0x%" PRIx64 " @ 0x%" PRIx64 ", offset: 0x%" PRIx64" next: 0x%" PRIx64 " mingap: 0x%" PRIx64
|
|
ram_block_discard_range(const char *rbname, void *hva, size_t length, bool need_madvise, bool need_fallocate, int ret) "%s@%p + 0x%zx: madvise: %d fallocate: %d ret: %d"
|
|
qemu_ram_alloc_shared(const char *name, size_t size, size_t max_size, int fd, void *host) "%s size %zu max_size %zu fd %d host %p"
|
|
|
|
# cpus.c
|
|
vm_stop_flush_all(int ret) "ret %d"
|
|
|
|
# vl.c
|
|
vm_state_notify(int running, int reason, const char *reason_str) "running %d reason %d (%s)"
|
|
load_file(const char *name, const char *path) "name %s location %s"
|
|
runstate_set(int current_state, const char *current_state_str, int new_state, const char *new_state_str) "current_run_state %d (%s) new_state %d (%s)"
|
|
system_wakeup_request(int reason) "reason=%d"
|
|
qemu_system_shutdown_request(int reason) "reason=%d"
|
|
qemu_system_powerdown_request(void) ""
|
|
|
|
#dirtylimit.c
|
|
dirtylimit_state_initialize(int max_cpus) "dirtylimit state initialize: max cpus %d"
|
|
dirtylimit_state_finalize(void)
|
|
dirtylimit_throttle_pct(int cpu_index, uint64_t pct, int64_t time_us) "CPU[%d] throttle percent: %" PRIu64 ", throttle adjust time %"PRIi64 " us"
|
|
dirtylimit_set_vcpu(int cpu_index, uint64_t quota) "CPU[%d] set dirty page rate limit %"PRIu64
|
|
dirtylimit_vcpu_execute(int cpu_index, int64_t sleep_time_us) "CPU[%d] sleep %"PRIi64 " us"
|
|
|
|
# ram-block-attributes.c
|
|
ram_block_attributes_state_change(uint64_t offset, uint64_t size, const char *from, const char *to) "offset 0x%"PRIx64" size 0x%"PRIx64" from '%s' to '%s'"
|